diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,14043 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.2238638907544213, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.00044772778150884264, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 0.0, + "loss": 0.0, + "num_tokens": 100884.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 1 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 981.0, + "completions/mean_length": 1023.328125, + "completions/mean_terminated_length": 981.0, + "completions/min_length": 981.0, + "completions/min_terminated_length": 981.0, + "epoch": 0.0008954555630176853, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.3333333333333335e-07, + "loss": 0.0, + "num_tokens": 206061.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 2 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 820.0, + "completions/mean_length": 1010.65625, + "completions/mean_terminated_length": 739.3333740234375, + "completions/min_length": 599.0, + "completions/min_terminated_length": 599.0, + "epoch": 0.001343183344526528, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.666666666666667e-07, + "loss": 0.0, + "num_tokens": 307747.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 3 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0017909111260353706, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0000000000000002e-06, + "loss": 0.0, + "num_tokens": 415135.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 4 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0022386389075442132, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3333333333333334e-06, + "loss": 0.0, + "num_tokens": 522827.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 5 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 855.0, + "completions/mean_length": 1018.6875, + "completions/mean_terminated_length": 854.0, + "completions/min_length": 853.0, + "completions/min_terminated_length": 853.0, + "epoch": 0.002686366689053056, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6666666666666667e-06, + "loss": 0.0, + "num_tokens": 624607.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 6 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 877.0, + "completions/mean_length": 1021.703125, + "completions/mean_terminated_length": 877.0, + "completions/min_length": 877.0, + "completions/min_terminated_length": 877.0, + "epoch": 0.0031340944705618985, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.0, + "num_tokens": 732704.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 7 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1000.0, + "completions/mean_length": 1023.625, + "completions/mean_terminated_length": 1000.0, + "completions/min_length": 1000.0, + "completions/min_terminated_length": 1000.0, + "epoch": 0.003581822252070741, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.3333333333333336e-06, + "loss": 0.0, + "num_tokens": 833560.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 8 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 931.0, + "completions/mean_length": 991.734375, + "completions/mean_terminated_length": 679.8333740234375, + "completions/min_length": 489.0, + "completions/min_terminated_length": 489.0, + "epoch": 0.004029550033579583, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.666666666666667e-06, + "loss": 0.0, + "num_tokens": 930871.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 9 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 940.0, + "completions/mean_length": 1017.6875, + "completions/mean_terminated_length": 822.0, + "completions/min_length": 704.0, + "completions/min_terminated_length": 704.0, + "epoch": 0.0044772778150884264, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3e-06, + "loss": 0.0, + "num_tokens": 1032675.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 10 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.004925005596597269, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.3333333333333333e-06, + "loss": 0.0, + "num_tokens": 1136951.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 11 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.005372733378106112, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.6666666666666666e-06, + "loss": 0.0, + "num_tokens": 1241799.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 12 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.005820461159614954, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.000000000000001e-06, + "loss": 0.0, + "num_tokens": 1353899.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 13 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 943.0, + "completions/mean_length": 1010.6875, + "completions/mean_terminated_length": 853.6000366210938, + "completions/min_length": 775.0, + "completions/min_terminated_length": 775.0, + "epoch": 0.006268188941123797, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.333333333333334e-06, + "loss": 0.0, + "num_tokens": 1461359.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 14 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.006715916722632639, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.666666666666667e-06, + "loss": 0.0, + "num_tokens": 1563783.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 15 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 983.0, + "completions/mean_length": 1014.640625, + "completions/mean_terminated_length": 824.3333740234375, + "completions/min_length": 634.0, + "completions/min_terminated_length": 634.0, + "epoch": 0.007163644504141482, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5e-06, + "loss": 0.0, + "num_tokens": 1667364.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 16 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 937.0, + "completions/mean_length": 1022.640625, + "completions/mean_terminated_length": 937.0, + "completions/min_length": 937.0, + "completions/min_terminated_length": 937.0, + "epoch": 0.0076113722856503245, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.999952797253148e-06, + "loss": 0.0, + "num_tokens": 1767621.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 17 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 695.0, + "completions/mean_length": 1018.859375, + "completions/mean_terminated_length": 695.0, + "completions/min_length": 695.0, + "completions/min_terminated_length": 695.0, + "epoch": 0.008059100067159167, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9998111909931225e-06, + "loss": 0.0, + "num_tokens": 1871276.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 18 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.00850682784866801, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.999575187161439e-06, + "loss": 0.0, + "num_tokens": 1969532.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 19 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1012.0, + "completions/mean_length": 1014.828125, + "completions/mean_terminated_length": 877.25, + "completions/min_length": 787.0, + "completions/min_terminated_length": 787.0, + "epoch": 0.008954555630176853, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9992447956603455e-06, + "loss": 0.0, + "num_tokens": 2073053.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 20 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.009402283411685695, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.998820030352409e-06, + "loss": 0.0, + "num_tokens": 2183973.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 21 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 696.0, + "completions/mean_length": 1018.875, + "completions/mean_terminated_length": 696.0, + "completions/min_length": 696.0, + "completions/min_terminated_length": 696.0, + "epoch": 0.009850011193194537, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.998300909059929e-06, + "loss": 0.0, + "num_tokens": 2283321.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 22 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 861.0, + "completions/mean_length": 968.453125, + "completions/mean_terminated_length": 579.625, + "completions/min_length": 369.0, + "completions/min_terminated_length": 369.0, + "epoch": 0.01029773897470338, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.997687453564198e-06, + "loss": 0.0, + "num_tokens": 2379834.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 23 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.010745466756212223, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9969796896045775e-06, + "loss": 0.0, + "num_tokens": 2482694.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 24 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 935.0, + "completions/mean_length": 1011.6875, + "completions/mean_terminated_length": 761.3333740234375, + "completions/min_length": 636.0, + "completions/min_terminated_length": 636.0, + "epoch": 0.011193194537721066, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.996177646877426e-06, + "loss": 0.0, + "num_tokens": 2588050.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 25 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.011640922319229908, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.995281359034851e-06, + "loss": 0.0, + "num_tokens": 2688946.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 26 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.01208865010073875, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.994290863683296e-06, + "loss": 0.0, + "num_tokens": 2799774.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 27 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.012536377882247594, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.99320620238196e-06, + "loss": 0.0, + "num_tokens": 2905150.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 28 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 872.0, + "completions/mean_length": 996.84375, + "completions/mean_terminated_length": 676.4000244140625, + "completions/min_length": 453.0, + "completions/min_terminated_length": 453.0, + "epoch": 0.012984105663756436, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.99202742064106e-06, + "loss": 0.0, + "num_tokens": 3009420.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 29 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 750.0, + "completions/mean_length": 1019.71875, + "completions/mean_terminated_length": 750.0, + "completions/min_length": 750.0, + "completions/min_terminated_length": 750.0, + "epoch": 0.013431833445265278, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.990754567919917e-06, + "loss": 0.0, + "num_tokens": 3111838.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 30 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 890.0, + "completions/mean_length": 1021.90625, + "completions/mean_terminated_length": 890.0, + "completions/min_length": 890.0, + "completions/min_terminated_length": 890.0, + "epoch": 0.01387956122677412, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.989387697624881e-06, + "loss": 0.0, + "num_tokens": 3219228.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 31 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.014327289008282965, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.987926867107095e-06, + "loss": 0.0, + "num_tokens": 3321704.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 32 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 458.0, + "completions/mean_length": 984.84375, + "completions/mean_terminated_length": 397.5, + "completions/min_length": 286.0, + "completions/min_terminated_length": 286.0, + "epoch": 0.014775016789791807, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.986372137660078e-06, + "loss": 0.0, + "num_tokens": 3416070.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 33 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 951.0, + "completions/mean_length": 1008.75, + "completions/mean_terminated_length": 780.0, + "completions/min_length": 690.0, + "completions/min_terminated_length": 690.0, + "epoch": 0.015222744571300649, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.984723574517165e-06, + "loss": 0.0, + "num_tokens": 3520162.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 34 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.01567047235280949, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9829812468487655e-06, + "loss": 0.0, + "num_tokens": 3626034.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 35 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.016118200134318333, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.981145227759457e-06, + "loss": 0.0, + "num_tokens": 3735634.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 36 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.016565927915827176, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.979215594284924e-06, + "loss": 0.0, + "num_tokens": 3835030.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 37 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 920.0, + "completions/mean_length": 1020.25, + "completions/mean_terminated_length": 904.0, + "completions/min_length": 888.0, + "completions/min_terminated_length": 888.0, + "epoch": 0.01701365569733602, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.977192427388722e-06, + "loss": 0.0, + "num_tokens": 3938066.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 38 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.017461383478844864, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9750758119588824e-06, + "loss": 0.0, + "num_tokens": 4042074.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 39 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.017909111260353706, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.972865836804349e-06, + "loss": 0.0, + "num_tokens": 4142166.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 40 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 969.0, + "completions/mean_length": 998.796875, + "completions/mean_terminated_length": 755.1666870117188, + "completions/min_length": 489.0, + "completions/min_terminated_length": 489.0, + "epoch": 0.018356839041862548, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.970562594651254e-06, + "loss": 0.0, + "num_tokens": 4243141.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 41 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 993.0, + "completions/mean_length": 1007.5, + "completions/mean_terminated_length": 760.0, + "completions/min_length": 380.0, + "completions/min_terminated_length": 380.0, + "epoch": 0.01880456682337139, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.968166182139026e-06, + "loss": 0.0, + "num_tokens": 4339925.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 42 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.019252294604880232, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9656766998163306e-06, + "loss": 0.0, + "num_tokens": 4440849.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 43 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 833.0, + "completions/mean_length": 1009.859375, + "completions/mean_terminated_length": 722.3333740234375, + "completions/min_length": 554.0, + "completions/min_terminated_length": 554.0, + "epoch": 0.019700022386389075, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.963094252136865e-06, + "loss": 0.0, + "num_tokens": 4542032.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 44 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1006.0, + "completions/mean_length": 1000.21875, + "completions/mean_terminated_length": 806.5714721679688, + "completions/min_length": 569.0, + "completions/min_terminated_length": 569.0, + "epoch": 0.020147750167897917, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.960418947454958e-06, + "loss": 0.0, + "num_tokens": 4641134.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 45 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.02059547794940676, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.957650898021038e-06, + "loss": 0.0, + "num_tokens": 4738942.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 46 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.021043205730915605, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.954790219976915e-06, + "loss": 0.0, + "num_tokens": 4843394.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 47 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 601.0, + "completions/mean_length": 987.03125, + "completions/mean_terminated_length": 432.5, + "completions/min_length": 328.0, + "completions/min_terminated_length": 328.0, + "epoch": 0.021490933512424447, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.95183703335091e-06, + "loss": 0.0, + "num_tokens": 4953276.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 48 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 691.0, + "completions/mean_length": 1018.796875, + "completions/mean_terminated_length": 691.0, + "completions/min_length": 691.0, + "completions/min_terminated_length": 691.0, + "epoch": 0.02193866129393329, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.948791462052819e-06, + "loss": 0.0, + "num_tokens": 5052115.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 49 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.02238638907544213, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.945653633868716e-06, + "loss": 0.0, + "num_tokens": 5150371.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 50 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 920.0, + "completions/mean_length": 1008.15625, + "completions/mean_terminated_length": 770.5, + "completions/min_length": 646.0, + "completions/min_terminated_length": 646.0, + "epoch": 0.022834116856950974, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.942423680455584e-06, + "loss": 0.0, + "num_tokens": 5253669.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 51 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.023281844638459816, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.939101737335802e-06, + "loss": 0.0, + "num_tokens": 5355089.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 52 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 866.0, + "completions/mean_length": 1007.34375, + "completions/mean_terminated_length": 810.7999877929688, + "completions/min_length": 758.0, + "completions/min_terminated_length": 758.0, + "epoch": 0.023729572419968658, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.935687943891447e-06, + "loss": 0.0, + "num_tokens": 5451299.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 53 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 925.0, + "completions/mean_length": 984.453125, + "completions/mean_terminated_length": 517.7999877929688, + "completions/min_length": 343.0, + "completions/min_terminated_length": 343.0, + "epoch": 0.0241773002014775, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.932182443358458e-06, + "loss": 0.0, + "num_tokens": 5549856.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 54 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 666.0, + "completions/mean_length": 995.84375, + "completions/mean_terminated_length": 573.5, + "completions/min_length": 447.0, + "completions/min_terminated_length": 447.0, + "epoch": 0.024625027982986346, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.928585382820616e-06, + "loss": 0.0, + "num_tokens": 5647106.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 55 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.025072755764495188, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.924896913203376e-06, + "loss": 0.0, + "num_tokens": 5749690.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 56 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1013.0, + "completions/mean_length": 1023.828125, + "completions/mean_terminated_length": 1013.0, + "completions/min_length": 1013.0, + "completions/min_terminated_length": 1013.0, + "epoch": 0.02552048354600403, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.921117189267535e-06, + "loss": 0.0, + "num_tokens": 5858495.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 57 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 934.0, + "completions/mean_length": 998.125, + "completions/mean_terminated_length": 787.4285888671875, + "completions/min_length": 651.0, + "completions/min_terminated_length": 651.0, + "epoch": 0.025968211327512872, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.917246369602742e-06, + "loss": 0.0, + "num_tokens": 5964883.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 58 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 881.0, + "completions/mean_length": 993.46875, + "completions/mean_terminated_length": 535.5, + "completions/min_length": 364.0, + "completions/min_terminated_length": 364.0, + "epoch": 0.026415939109021715, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9132846166208355e-06, + "loss": 0.0, + "num_tokens": 6070717.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 59 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.026863666890530557, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.9092320965490365e-06, + "loss": 0.0, + "num_tokens": 6167285.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 60 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1010.0, + "completions/mean_length": 1007.875, + "completions/mean_terminated_length": 817.6000366210938, + "completions/min_length": 630.0, + "completions/min_terminated_length": 630.0, + "epoch": 0.0273113946720394, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.905088979422971e-06, + "loss": 0.0, + "num_tokens": 6269273.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 61 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.02775912245354824, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.900855439079536e-06, + "loss": 0.0, + "num_tokens": 6369913.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 62 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 796.0, + "completions/mean_length": 1000.015625, + "completions/mean_terminated_length": 640.25, + "completions/min_length": 387.0, + "completions/min_terminated_length": 387.0, + "epoch": 0.028206850235057087, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.8965316531496055e-06, + "loss": 0.0, + "num_tokens": 6472778.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 63 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1000.0, + "completions/mean_length": 1023.625, + "completions/mean_terminated_length": 1000.0, + "completions/min_length": 1000.0, + "completions/min_terminated_length": 1000.0, + "epoch": 0.02865457801656593, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.892117803050578e-06, + "loss": 0.0, + "num_tokens": 6582038.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 64 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.02910230579807477, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.887614073978761e-06, + "loss": 0.0, + "num_tokens": 6687850.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 65 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.029550033579583614, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.883020654901609e-06, + "loss": 0.0, + "num_tokens": 6790154.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 66 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 888.0, + "completions/mean_length": 1019.171875, + "completions/mean_terminated_length": 869.5, + "completions/min_length": 851.0, + "completions/min_terminated_length": 851.0, + "epoch": 0.029997761361092456, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.878337738549785e-06, + "loss": 0.0, + "num_tokens": 6885773.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 67 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.030445489142601298, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.873565521409082e-06, + "loss": 0.0, + "num_tokens": 6990045.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 68 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03089321692411014, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.868704203712173e-06, + "loss": 0.0, + "num_tokens": 7095261.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 69 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 947.0, + "completions/mean_length": 986.59375, + "completions/mean_terminated_length": 724.75, + "completions/min_length": 609.0, + "completions/min_terminated_length": 609.0, + "epoch": 0.03134094470561898, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.86375398943021e-06, + "loss": 0.0, + "num_tokens": 7197803.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 70 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03178867248712783, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.858715086264274e-06, + "loss": 0.0, + "num_tokens": 7300623.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 71 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 993.0, + "completions/mean_length": 1022.25, + "completions/mean_terminated_length": 968.0, + "completions/min_length": 943.0, + "completions/min_terminated_length": 943.0, + "epoch": 0.03223640026863667, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.853587705636646e-06, + "loss": 0.0, + "num_tokens": 7404155.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 72 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 642.0, + "completions/mean_length": 994.90625, + "completions/mean_terminated_length": 558.5, + "completions/min_length": 495.0, + "completions/min_terminated_length": 495.0, + "epoch": 0.03268412805014551, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.84837206268195e-06, + "loss": 0.0, + "num_tokens": 7507393.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 73 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03313185583165435, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.8430683762381195e-06, + "loss": 0.0, + "num_tokens": 7607517.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 74 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0335795836131632, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.837676868837213e-06, + "loss": 0.0, + "num_tokens": 7712433.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 75 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03402731139467204, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.832197766696085e-06, + "loss": 0.0, + "num_tokens": 7815861.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 76 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03447503917618088, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.826631299706887e-06, + "loss": 0.0, + "num_tokens": 7920797.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 77 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 980.0, + "completions/mean_length": 1016.96875, + "completions/mean_terminated_length": 874.0, + "completions/min_length": 757.0, + "completions/min_terminated_length": 757.0, + "epoch": 0.03492276695768973, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.820977701427424e-06, + "loss": 0.0, + "num_tokens": 8021783.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 78 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 866.0, + "completions/mean_length": 1021.53125, + "completions/mean_terminated_length": 866.0, + "completions/min_length": 866.0, + "completions/min_terminated_length": 866.0, + "epoch": 0.035370494739198566, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.81523720907136e-06, + "loss": 0.0, + "num_tokens": 8120937.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 79 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03581822252070741, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.809410063498254e-06, + "loss": 0.0, + "num_tokens": 8225273.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 80 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1018.0, + "completions/mean_length": 1021.46875, + "completions/mean_terminated_length": 970.0, + "completions/min_length": 915.0, + "completions/min_terminated_length": 915.0, + "epoch": 0.03626595030221625, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.8034965092034656e-06, + "loss": 0.0, + "num_tokens": 8328119.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 81 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.036713678083725096, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.797496794307889e-06, + "loss": 0.0, + "num_tokens": 8423835.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 82 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 911.0, + "completions/mean_length": 1017.0, + "completions/mean_terminated_length": 874.6666870117188, + "completions/min_length": 836.0, + "completions/min_terminated_length": 836.0, + "epoch": 0.037161405865233935, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.791411170547545e-06, + "loss": 0.0, + "num_tokens": 8523827.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 83 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.03760913364674278, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.785239893263017e-06, + "loss": 0.0, + "num_tokens": 8632007.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 84 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 985.0, + "completions/mean_length": 1020.0, + "completions/mean_terminated_length": 960.0, + "completions/min_length": 944.0, + "completions/min_terminated_length": 944.0, + "epoch": 0.038056861428251626, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.778983221388742e-06, + "loss": 0.0, + "num_tokens": 8729159.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 85 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.038504589209760465, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.77264141744214e-06, + "loss": 0.0, + "num_tokens": 8828767.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 86 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1008.0, + "completions/mean_length": 1020.9375, + "completions/mean_terminated_length": 926.0, + "completions/min_length": 844.0, + "completions/min_terminated_length": 844.0, + "epoch": 0.03895231699126931, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.766214747512603e-06, + "loss": 0.0, + "num_tokens": 8928211.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 87 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 939.0, + "completions/mean_length": 1022.671875, + "completions/mean_terminated_length": 939.0, + "completions/min_length": 939.0, + "completions/min_terminated_length": 939.0, + "epoch": 0.03940004477277815, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.759703481250331e-06, + "loss": 0.0, + "num_tokens": 9030762.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 88 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 966.0, + "completions/mean_length": 1013.359375, + "completions/mean_terminated_length": 797.0, + "completions/min_length": 598.0, + "completions/min_terminated_length": 598.0, + "epoch": 0.039847772554286995, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.753107891855015e-06, + "loss": 0.0, + "num_tokens": 9137589.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 89 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.040295500335795834, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.746428256064375e-06, + "loss": 0.0, + "num_tokens": 9241461.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 90 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 867.0, + "completions/mean_length": 975.953125, + "completions/mean_terminated_length": 639.625, + "completions/min_length": 419.0, + "completions/min_terminated_length": 419.0, + "epoch": 0.04074322811730468, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.7396648541425534e-06, + "loss": 0.0, + "num_tokens": 9338218.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 91 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.04119095589881352, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.732817969868348e-06, + "loss": 0.0, + "num_tokens": 9443666.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 92 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 836.0, + "completions/mean_length": 1021.0625, + "completions/mean_terminated_length": 836.0, + "completions/min_length": 836.0, + "completions/min_terminated_length": 836.0, + "epoch": 0.041638683680322364, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.7258878905233095e-06, + "loss": 0.0, + "num_tokens": 9545246.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 93 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.04208641146183121, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.718874906879688e-06, + "loss": 0.0, + "num_tokens": 9650522.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 94 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.04253413924334005, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.711779313188231e-06, + "loss": 0.0, + "num_tokens": 9756938.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 95 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 986.0, + "completions/mean_length": 1023.40625, + "completions/mean_terminated_length": 986.0, + "completions/min_length": 986.0, + "completions/min_terminated_length": 986.0, + "epoch": 0.042981867024848894, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.70460140716584e-06, + "loss": 0.0, + "num_tokens": 9865392.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 96 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.04342959480635773, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.697341489983076e-06, + "loss": 0.0, + "num_tokens": 9965916.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 97 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.04387732258786658, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.6899998662515215e-06, + "loss": 0.0, + "num_tokens": 10066196.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 98 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 922.0, + "completions/mean_length": 1012.953125, + "completions/mean_terminated_length": 670.5, + "completions/min_length": 419.0, + "completions/min_terminated_length": 419.0, + "epoch": 0.04432505036937542, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.682576844011007e-06, + "loss": 0.0, + "num_tokens": 10168765.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 99 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.04477277815088426, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.675072734716678e-06, + "loss": 0.0, + "num_tokens": 10273713.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 100 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 932.0, + "completions/mean_length": 1022.5625, + "completions/mean_terminated_length": 932.0, + "completions/min_length": 932.0, + "completions/min_terminated_length": 932.0, + "epoch": 0.04522050593239311, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.667487853225931e-06, + "loss": 0.0, + "num_tokens": 10378013.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 101 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 503.0, + "completions/mean_length": 1015.859375, + "completions/mean_terminated_length": 503.0, + "completions/min_length": 503.0, + "completions/min_terminated_length": 503.0, + "epoch": 0.04566823371390195, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.659822517785203e-06, + "loss": 0.0, + "num_tokens": 10478420.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 102 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 648.0, + "completions/mean_length": 995.65625, + "completions/mean_terminated_length": 570.5, + "completions/min_length": 492.0, + "completions/min_terminated_length": 492.0, + "epoch": 0.04611596149541079, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.6520770500166165e-06, + "loss": 0.0, + "num_tokens": 10575242.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 103 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 913.0, + "completions/mean_length": 1019.953125, + "completions/mean_terminated_length": 894.5, + "completions/min_length": 876.0, + "completions/min_terminated_length": 876.0, + "epoch": 0.04656368927691963, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.644251774904487e-06, + "loss": 0.0, + "num_tokens": 10679227.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 104 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 870.0, + "completions/mean_length": 983.453125, + "completions/mean_terminated_length": 505.0, + "completions/min_length": 327.0, + "completions/min_terminated_length": 327.0, + "epoch": 0.04701141705842848, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.636347020781684e-06, + "loss": 0.0, + "num_tokens": 10775676.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 105 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 969.0, + "completions/mean_length": 1017.046875, + "completions/mean_terminated_length": 801.5, + "completions/min_length": 634.0, + "completions/min_terminated_length": 634.0, + "epoch": 0.047459144839937316, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.6283631193158605e-06, + "loss": 0.0, + "num_tokens": 10880815.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 106 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 688.0, + "completions/mean_length": 1012.09375, + "completions/mean_terminated_length": 643.0, + "completions/min_length": 598.0, + "completions/min_terminated_length": 598.0, + "epoch": 0.04790687262144616, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.620300405495532e-06, + "loss": 0.0, + "num_tokens": 10986009.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 107 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.048354600402955, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.612159217616022e-06, + "loss": 0.0, + "num_tokens": 11090309.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 108 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 681.0, + "completions/mean_length": 997.25, + "completions/mean_terminated_length": 596.0, + "completions/min_length": 494.0, + "completions/min_terminated_length": 494.0, + "epoch": 0.048802328184463846, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.603939897265268e-06, + "loss": 0.0, + "num_tokens": 11186605.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 109 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 723.0, + "completions/mean_length": 997.046875, + "completions/mean_terminated_length": 592.75, + "completions/min_length": 507.0, + "completions/min_terminated_length": 507.0, + "epoch": 0.04925005596597269, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.595642789309492e-06, + "loss": 0.0, + "num_tokens": 11282088.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 110 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 992.0, + "completions/mean_length": 1023.5, + "completions/mean_terminated_length": 992.0, + "completions/min_length": 992.0, + "completions/min_terminated_length": 992.0, + "epoch": 0.04969778374748153, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.587268241878724e-06, + "loss": 0.0, + "num_tokens": 11385668.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 111 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.050145511528990376, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.578816606352205e-06, + "loss": 0.0, + "num_tokens": 11490012.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 112 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.050593239310499215, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.570288237343632e-06, + "loss": 0.0, + "num_tokens": 11594964.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 113 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 857.0, + "completions/mean_length": 1005.765625, + "completions/mean_terminated_length": 732.25, + "completions/min_length": 644.0, + "completions/min_terminated_length": 644.0, + "epoch": 0.05104096709200806, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.561683492686289e-06, + "loss": 0.0, + "num_tokens": 11696097.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 114 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0514886948735169, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.5530027334180285e-06, + "loss": 0.0, + "num_tokens": 11803213.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 115 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 930.0, + "completions/mean_length": 1011.75, + "completions/mean_terminated_length": 762.6666870117188, + "completions/min_length": 659.0, + "completions/min_terminated_length": 659.0, + "epoch": 0.051936422655025745, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.544246323766122e-06, + "loss": 0.0, + "num_tokens": 11904105.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 116 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1004.0, + "completions/mean_length": 1014.3125, + "completions/mean_terminated_length": 869.0, + "completions/min_length": 687.0, + "completions/min_terminated_length": 687.0, + "epoch": 0.052384150436534584, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.535414631131983e-06, + "loss": 0.0, + "num_tokens": 12010265.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 117 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1021.0, + "completions/mean_length": 1004.75, + "completions/mean_terminated_length": 887.1111450195312, + "completions/min_length": 824.0, + "completions/min_terminated_length": 824.0, + "epoch": 0.05283187821804343, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.526508026075746e-06, + "loss": 0.0, + "num_tokens": 12109857.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 118 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.053279605999552275, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.517526882300721e-06, + "loss": 0.0, + "num_tokens": 12212909.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 119 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 579.0, + "completions/mean_length": 1017.046875, + "completions/mean_terminated_length": 579.0, + "completions/min_length": 579.0, + "completions/min_terminated_length": 579.0, + "epoch": 0.053727333781061114, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.508471576637713e-06, + "loss": 0.0, + "num_tokens": 12318084.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 120 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.05417506156256996, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.499342489029211e-06, + "loss": 0.0, + "num_tokens": 12422824.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 121 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1016.0, + "completions/mean_length": 997.21875, + "completions/mean_terminated_length": 681.2000122070312, + "completions/min_length": 502.0, + "completions/min_terminated_length": 502.0, + "epoch": 0.0546227893440788, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.490140002513449e-06, + "loss": 0.0, + "num_tokens": 12527674.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 122 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 707.0, + "completions/mean_length": 1006.28125, + "completions/mean_terminated_length": 646.0, + "completions/min_length": 580.0, + "completions/min_terminated_length": 580.0, + "epoch": 0.055070517125587644, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.48086450320833e-06, + "loss": 0.0, + "num_tokens": 12627868.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 123 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 894.0, + "completions/mean_length": 1018.59375, + "completions/mean_terminated_length": 851.0, + "completions/min_length": 808.0, + "completions/min_terminated_length": 808.0, + "epoch": 0.05551824490709648, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.4715163802952266e-06, + "loss": 0.0, + "num_tokens": 12730554.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 124 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.05596597268860533, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.462096026002655e-06, + "loss": 0.0, + "num_tokens": 12833422.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 125 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1005.0, + "completions/mean_length": 1018.03125, + "completions/mean_terminated_length": 896.6666870117188, + "completions/min_length": 811.0, + "completions/min_terminated_length": 811.0, + "epoch": 0.056413700470114174, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.4526038355898144e-06, + "loss": 0.0, + "num_tokens": 12937280.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 126 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.05686142825162301, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.4430402073300035e-06, + "loss": 0.0, + "num_tokens": 13041688.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 127 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1003.0, + "completions/mean_length": 1003.296875, + "completions/mean_terminated_length": 834.7142944335938, + "completions/min_length": 671.0, + "completions/min_terminated_length": 671.0, + "epoch": 0.05730915603313186, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.433405542493909e-06, + "loss": 0.0, + "num_tokens": 13137275.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 128 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 595.0, + "completions/mean_length": 990.3125, + "completions/mean_terminated_length": 485.0, + "completions/min_length": 407.0, + "completions/min_terminated_length": 407.0, + "epoch": 0.0577568838146407, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.4237002453327734e-06, + "loss": 0.0, + "num_tokens": 13238395.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 129 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 944.0, + "completions/mean_length": 1012.59375, + "completions/mean_terminated_length": 780.6666870117188, + "completions/min_length": 644.0, + "completions/min_terminated_length": 644.0, + "epoch": 0.05820461159614954, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.4139247230614245e-06, + "loss": 0.0, + "num_tokens": 13340133.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 130 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.05865233937765838, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.404079385841201e-06, + "loss": 0.0, + "num_tokens": 13446217.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 131 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 750.0, + "completions/mean_length": 993.484375, + "completions/mean_terminated_length": 535.75, + "completions/min_length": 407.0, + "completions/min_terminated_length": 407.0, + "epoch": 0.05910006715916723, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.394164646762734e-06, + "loss": 0.0, + "num_tokens": 13549708.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 132 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.059547794940676066, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.384180921828618e-06, + "loss": 0.0, + "num_tokens": 13651832.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 133 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 746.0, + "completions/mean_length": 1019.65625, + "completions/mean_terminated_length": 746.0, + "completions/min_length": 746.0, + "completions/min_terminated_length": 746.0, + "epoch": 0.05999552272218491, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.374128629935955e-06, + "loss": 0.0, + "num_tokens": 13756070.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 134 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06044325050369376, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.364008192858781e-06, + "loss": 0.0, + "num_tokens": 13857318.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 135 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.060890978285202596, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.353820035230366e-06, + "loss": 0.0, + "num_tokens": 13965146.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 136 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 904.0, + "completions/mean_length": 1004.984375, + "completions/mean_terminated_length": 719.75, + "completions/min_length": 548.0, + "completions/min_terminated_length": 548.0, + "epoch": 0.06133870606671144, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.3435645845254e-06, + "loss": 0.0, + "num_tokens": 14065581.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 137 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06178643384822028, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.333242271042054e-06, + "loss": 0.0, + "num_tokens": 14166301.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 138 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.062234161629729126, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.32285352788393e-06, + "loss": 0.0, + "num_tokens": 14270261.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 139 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 919.0, + "completions/mean_length": 1013.96875, + "completions/mean_terminated_length": 863.5, + "completions/min_length": 797.0, + "completions/min_terminated_length": 797.0, + "epoch": 0.06268188941123796, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.312398790941882e-06, + "loss": 0.0, + "num_tokens": 14371047.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 140 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0631296171927468, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.301878498875735e-06, + "loss": 0.0, + "num_tokens": 14476499.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 141 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06357734497425566, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.291293093095873e-06, + "loss": 0.0, + "num_tokens": 14579207.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 142 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 839.0, + "completions/mean_length": 1021.109375, + "completions/mean_terminated_length": 839.0, + "completions/min_length": 839.0, + "completions/min_terminated_length": 839.0, + "epoch": 0.0640250727557645, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.280643017744723e-06, + "loss": 0.0, + "num_tokens": 14686978.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 143 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06447280053727333, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.269928719678117e-06, + "loss": 0.0, + "num_tokens": 14792318.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 144 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 977.0, + "completions/mean_length": 1021.03125, + "completions/mean_terminated_length": 929.0, + "completions/min_length": 881.0, + "completions/min_terminated_length": 881.0, + "epoch": 0.06492052831878219, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.2591506484465426e-06, + "loss": 0.0, + "num_tokens": 14892548.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 145 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 932.0, + "completions/mean_length": 995.125, + "completions/mean_terminated_length": 818.6666870117188, + "completions/min_length": 643.0, + "completions/min_terminated_length": 643.0, + "epoch": 0.06536825610029103, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.248309256276283e-06, + "loss": 0.0, + "num_tokens": 14988564.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 146 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1018.0, + "completions/mean_length": 1005.8125, + "completions/mean_terminated_length": 878.5, + "completions/min_length": 715.0, + "completions/min_terminated_length": 715.0, + "epoch": 0.06581598388179986, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.23740499805044e-06, + "loss": 0.0, + "num_tokens": 15086448.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 147 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 507.0, + "completions/mean_length": 987.0625, + "completions/mean_terminated_length": 433.0, + "completions/min_length": 355.0, + "completions/min_terminated_length": 355.0, + "epoch": 0.0662637116633087, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.22643833128985e-06, + "loss": 0.0, + "num_tokens": 15185412.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 148 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1021.0, + "completions/mean_length": 1023.953125, + "completions/mean_terminated_length": 1021.0, + "completions/min_length": 1021.0, + "completions/min_terminated_length": 1021.0, + "epoch": 0.06671143944481756, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.215409716133885e-06, + "loss": 0.0, + "num_tokens": 15283373.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 149 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0671591672263264, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.204319615321151e-06, + "loss": 0.0, + "num_tokens": 15391997.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 150 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 991.0, + "completions/mean_length": 965.359375, + "completions/mean_terminated_length": 607.0, + "completions/min_length": 276.0, + "completions/min_terminated_length": 276.0, + "epoch": 0.06760689500783523, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.193168494170065e-06, + "loss": 0.0, + "num_tokens": 15488724.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 151 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1008.0, + "completions/mean_length": 1019.40625, + "completions/mean_terminated_length": 877.0, + "completions/min_length": 746.0, + "completions/min_terminated_length": 746.0, + "epoch": 0.06805462278934409, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.181956820559339e-06, + "loss": 0.0, + "num_tokens": 15587878.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 152 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06850235057085292, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.170685064908342e-06, + "loss": 0.0, + "num_tokens": 15695850.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 153 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06895007835236176, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.159353700157365e-06, + "loss": 0.0, + "num_tokens": 15795302.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 154 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0693978061338706, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.14796320174778e-06, + "loss": 0.0, + "num_tokens": 15898322.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 155 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.06984553391537945, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.136514047602087e-06, + "loss": 0.0, + "num_tokens": 15995538.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 156 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1022.0, + "completions/mean_length": 1012.625, + "completions/mean_terminated_length": 781.3333740234375, + "completions/min_length": 584.0, + "completions/min_terminated_length": 584.0, + "epoch": 0.07029326169688829, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.1250067181038635e-06, + "loss": 0.0, + "num_tokens": 16096670.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 157 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 745.0, + "completions/mean_length": 1019.640625, + "completions/mean_terminated_length": 745.0, + "completions/min_length": 745.0, + "completions/min_terminated_length": 745.0, + "epoch": 0.07074098947839713, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.113441696077608e-06, + "loss": 0.0, + "num_tokens": 16204591.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 158 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07118871725990597, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.101819466768484e-06, + "loss": 0.0, + "num_tokens": 16308059.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 159 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07163644504141482, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.0901405178219535e-06, + "loss": 0.0, + "num_tokens": 16413043.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 160 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 995.0, + "completions/mean_length": 1011.875, + "completions/mean_terminated_length": 830.0, + "completions/min_length": 598.0, + "completions/min_terminated_length": 598.0, + "epoch": 0.07208417282292366, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.078405339263326e-06, + "loss": 0.0, + "num_tokens": 16518911.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 161 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0725319006044325, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.06661442347719e-06, + "loss": 0.0, + "num_tokens": 16623503.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 162 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07297962838594135, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.054768265186758e-06, + "loss": 0.0, + "num_tokens": 16728267.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 163 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07342735616745019, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.0428673614331036e-06, + "loss": 0.0, + "num_tokens": 16830239.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 164 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07387508394895903, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.030912211554316e-06, + "loss": 0.0, + "num_tokens": 16933787.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 165 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 905.0, + "completions/mean_length": 986.140625, + "completions/mean_terminated_length": 677.857177734375, + "completions/min_length": 487.0, + "completions/min_terminated_length": 487.0, + "epoch": 0.07432281173046787, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.018903317164539e-06, + "loss": 0.0, + "num_tokens": 17037996.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 166 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07477053951197672, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 4.006841182132932e-06, + "loss": 0.0, + "num_tokens": 17145620.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 167 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 931.0, + "completions/mean_length": 1020.421875, + "completions/mean_terminated_length": 909.5, + "completions/min_length": 888.0, + "completions/min_terminated_length": 888.0, + "epoch": 0.07521826729348556, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.9947263125625195e-06, + "loss": 0.0, + "num_tokens": 17249783.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 168 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 798.0, + "completions/mean_length": 993.34375, + "completions/mean_terminated_length": 533.5, + "completions/min_length": 396.0, + "completions/min_terminated_length": 396.0, + "epoch": 0.0756659950749944, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.982559216768967e-06, + "loss": 0.0, + "num_tokens": 17348369.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 169 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07611372285650325, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.970340405259245e-06, + "loss": 0.0, + "num_tokens": 17452465.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 170 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07656145063801209, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.958070390710214e-06, + "loss": 0.0, + "num_tokens": 17556909.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 171 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07700917841952093, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.945749687947109e-06, + "loss": 0.0, + "num_tokens": 17661857.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 172 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07745690620102977, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.933378813921942e-06, + "loss": 0.0, + "num_tokens": 17763561.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 173 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07790463398253862, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.920958287691811e-06, + "loss": 0.0, + "num_tokens": 17868733.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 174 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 869.0, + "completions/mean_length": 1021.578125, + "completions/mean_terminated_length": 869.0, + "completions/min_length": 869.0, + "completions/min_terminated_length": 869.0, + "epoch": 0.07835236176404746, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.908488630397121e-06, + "loss": 0.0, + "num_tokens": 17968722.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 175 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 981.0, + "completions/mean_length": 1023.328125, + "completions/mean_terminated_length": 981.0, + "completions/min_length": 981.0, + "completions/min_terminated_length": 981.0, + "epoch": 0.0788000895455563, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.8959703652397175e-06, + "loss": 0.0, + "num_tokens": 18077271.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 176 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07924781732706515, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.883404017460935e-06, + "loss": 0.0, + "num_tokens": 18186387.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 177 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.07969554510857399, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.870790114319559e-06, + "loss": 0.0, + "num_tokens": 18291707.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 178 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 624.0, + "completions/mean_length": 999.5625, + "completions/mean_terminated_length": 502.66668701171875, + "completions/min_length": 433.0, + "completions/min_terminated_length": 433.0, + "epoch": 0.08014327289008283, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.858129185069701e-06, + "loss": 0.0, + "num_tokens": 18392119.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 179 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 992.0, + "completions/mean_length": 1004.328125, + "completions/mean_terminated_length": 772.2000122070312, + "completions/min_length": 652.0, + "completions/min_terminated_length": 652.0, + "epoch": 0.08059100067159167, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.845421760938597e-06, + "loss": 0.0, + "num_tokens": 18495344.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 180 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 951.0, + "completions/mean_length": 970.53125, + "completions/mean_terminated_length": 681.7999877929688, + "completions/min_length": 520.0, + "completions/min_terminated_length": 520.0, + "epoch": 0.08103872845310052, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.832668375104312e-06, + "loss": 0.0, + "num_tokens": 18595910.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 181 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08148645623460936, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.8198695626733725e-06, + "loss": 0.0, + "num_tokens": 18697342.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 182 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.0819341840161182, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.8070258606583156e-06, + "loss": 0.0, + "num_tokens": 18802114.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 183 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 959.0, + "completions/mean_length": 1002.5625, + "completions/mean_terminated_length": 795.3333740234375, + "completions/min_length": 605.0, + "completions/min_terminated_length": 605.0, + "epoch": 0.08238191179762704, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.7941378079551544e-06, + "loss": 0.0, + "num_tokens": 18905054.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 184 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08282963957913589, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.7812059453207677e-06, + "loss": 0.0, + "num_tokens": 19010542.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 185 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08327736736064473, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.768230815350213e-06, + "loss": 0.0, + "num_tokens": 19115434.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 186 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08372509514215357, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.7552129624539557e-06, + "loss": 0.0, + "num_tokens": 19217818.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 187 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08417282292366242, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.7421529328350316e-06, + "loss": 0.0, + "num_tokens": 19319702.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 188 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 982.0, + "completions/mean_length": 994.25, + "completions/mean_terminated_length": 786.0, + "completions/min_length": 575.0, + "completions/min_terminated_length": 575.0, + "epoch": 0.08462055070517126, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.7290512744661274e-06, + "loss": 0.0, + "num_tokens": 19413710.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 189 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 889.0, + "completions/mean_length": 1015.21875, + "completions/mean_terminated_length": 836.6666870117188, + "completions/min_length": 762.0, + "completions/min_terminated_length": 762.0, + "epoch": 0.0850682784866801, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.715908537066589e-06, + "loss": 0.0, + "num_tokens": 19514196.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 190 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 606.0, + "completions/mean_length": 992.703125, + "completions/mean_terminated_length": 523.25, + "completions/min_length": 424.0, + "completions/min_terminated_length": 424.0, + "epoch": 0.08551600626818893, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.7027252720793538e-06, + "loss": 0.0, + "num_tokens": 19613753.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 191 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08596373404969779, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.689502032647817e-06, + "loss": 0.0, + "num_tokens": 19720729.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 192 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 972.0, + "completions/mean_length": 1023.1875, + "completions/mean_terminated_length": 972.0, + "completions/min_length": 972.0, + "completions/min_terminated_length": 972.0, + "epoch": 0.08641146183120663, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.6762393735926245e-06, + "loss": 0.0, + "num_tokens": 19821269.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 193 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 745.0, + "completions/mean_length": 1019.640625, + "completions/mean_terminated_length": 745.0, + "completions/min_length": 745.0, + "completions/min_terminated_length": 745.0, + "epoch": 0.08685918961271547, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.6629378513883852e-06, + "loss": 0.0, + "num_tokens": 19921210.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 194 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 663.0, + "completions/mean_length": 1018.359375, + "completions/mean_terminated_length": 663.0, + "completions/min_length": 663.0, + "completions/min_terminated_length": 663.0, + "epoch": 0.08730691739422432, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.6495980241403307e-06, + "loss": 0.0, + "num_tokens": 20024277.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 195 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08775464517573316, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.636220451560896e-06, + "loss": 0.0, + "num_tokens": 20130741.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 196 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.088202372957242, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.622805694946235e-06, + "loss": 0.0, + "num_tokens": 20231521.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 197 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1006.0, + "completions/mean_length": 1019.0625, + "completions/mean_terminated_length": 945.0, + "completions/min_length": 838.0, + "completions/min_terminated_length": 838.0, + "epoch": 0.08865010073875083, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.609354317152667e-06, + "loss": 0.0, + "num_tokens": 20334933.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 198 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08909782852025969, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.595866882573063e-06, + "loss": 0.0, + "num_tokens": 20431537.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 199 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08954555630176853, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.5823439571131675e-06, + "loss": 0.0, + "num_tokens": 20535769.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 200 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.08999328408327736, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.5687861081678477e-06, + "loss": 0.0, + "num_tokens": 20640141.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 201 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09044101186478622, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.555193904597291e-06, + "loss": 0.0, + "num_tokens": 20748021.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 202 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 970.0, + "completions/mean_length": 984.84375, + "completions/mean_terminated_length": 710.75, + "completions/min_length": 439.0, + "completions/min_terminated_length": 439.0, + "epoch": 0.09088873964629506, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.541567916703138e-06, + "loss": 0.0, + "num_tokens": 20850671.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 203 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 949.0, + "completions/mean_length": 1015.828125, + "completions/mean_terminated_length": 849.6666870117188, + "completions/min_length": 735.0, + "completions/min_terminated_length": 735.0, + "epoch": 0.0913364674278039, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.5279087162045517e-06, + "loss": 0.0, + "num_tokens": 20946692.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 204 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09178419520931273, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.5142168762142265e-06, + "loss": 0.0, + "num_tokens": 21048832.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 205 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09223192299082159, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.500492971214347e-06, + "loss": 0.0, + "num_tokens": 21154204.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 206 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09267965077233042, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.48673757703248e-06, + "loss": 0.0, + "num_tokens": 21263912.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 207 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09312737855383926, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.472951270817418e-06, + "loss": 0.0, + "num_tokens": 21369804.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 208 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1014.0, + "completions/mean_length": 1017.53125, + "completions/mean_terminated_length": 817.0, + "completions/min_length": 620.0, + "completions/min_terminated_length": 620.0, + "epoch": 0.0935751063353481, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.4591346310149578e-06, + "loss": 0.0, + "num_tokens": 21470438.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 209 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 676.0, + "completions/mean_length": 999.359375, + "completions/mean_terminated_length": 629.75, + "completions/min_length": 516.0, + "completions/min_terminated_length": 516.0, + "epoch": 0.09402283411685695, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.445288237343632e-06, + "loss": 0.0, + "num_tokens": 21570277.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 210 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 868.0, + "completions/mean_length": 1004.15625, + "completions/mean_terminated_length": 770.0, + "completions/min_length": 542.0, + "completions/min_terminated_length": 542.0, + "epoch": 0.09447056189836579, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.4314126707703895e-06, + "loss": 0.0, + "num_tokens": 21669423.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 211 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 803.0, + "completions/mean_length": 1006.96875, + "completions/mean_terminated_length": 751.5, + "completions/min_length": 689.0, + "completions/min_terminated_length": 689.0, + "epoch": 0.09491828967987463, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.4175085134862128e-06, + "loss": 0.0, + "num_tokens": 21767317.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 212 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09536601746138348, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.4035763488816953e-06, + "loss": 0.0, + "num_tokens": 21867173.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 213 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09581374524289232, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.3896167615225594e-06, + "loss": 0.0, + "num_tokens": 21966625.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 214 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09626147302440116, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.375630337125133e-06, + "loss": 0.0, + "num_tokens": 22073941.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 215 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09670920080591, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.361617662531772e-06, + "loss": 0.0, + "num_tokens": 22178133.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 216 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09715692858741885, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.347579325686237e-06, + "loss": 0.0, + "num_tokens": 22278497.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 217 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.09760465636892769, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.333515915609027e-06, + "loss": 0.0, + "num_tokens": 22381605.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 218 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 848.0, + "completions/mean_length": 1021.25, + "completions/mean_terminated_length": 848.0, + "completions/min_length": 848.0, + "completions/min_terminated_length": 848.0, + "epoch": 0.09805238415043653, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.3194280223726616e-06, + "loss": 0.0, + "num_tokens": 22483869.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 219 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 974.0, + "completions/mean_length": 1006.90625, + "completions/mean_terminated_length": 750.5, + "completions/min_length": 641.0, + "completions/min_terminated_length": 641.0, + "epoch": 0.09850011193194538, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.305316237076927e-06, + "loss": 0.0, + "num_tokens": 22583423.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 220 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1010.0, + "completions/mean_length": 1022.140625, + "completions/mean_terminated_length": 984.3333740234375, + "completions/min_length": 947.0, + "completions/min_terminated_length": 947.0, + "epoch": 0.09894783971345422, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.291181151824071e-06, + "loss": 0.0, + "num_tokens": 22682332.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 221 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 957.0, + "completions/mean_length": 960.375, + "completions/mean_terminated_length": 571.5555419921875, + "completions/min_length": 253.0, + "completions/min_terminated_length": 253.0, + "epoch": 0.09939556749496306, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.27702335969396e-06, + "loss": 0.0, + "num_tokens": 22777036.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 222 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 814.0, + "completions/mean_length": 1004.890625, + "completions/mean_terminated_length": 718.25, + "completions/min_length": 605.0, + "completions/min_terminated_length": 605.0, + "epoch": 0.0998432952764719, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.2628434547191985e-06, + "loss": 0.0, + "num_tokens": 22875313.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 223 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10029102305798075, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.2486420318601973e-06, + "loss": 0.0, + "num_tokens": 22983061.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 224 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10073875083948959, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.2344196869802187e-06, + "loss": 0.0, + "num_tokens": 23083065.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 225 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10118647862099843, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.2201770168203694e-06, + "loss": 0.0, + "num_tokens": 23188249.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 226 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 994.0, + "completions/mean_length": 1002.671875, + "completions/mean_terminated_length": 829.0000610351562, + "completions/min_length": 663.0, + "completions/min_terminated_length": 663.0, + "epoch": 0.10163420640250728, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.205914618974563e-06, + "loss": 0.0, + "num_tokens": 23289060.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 227 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 974.0, + "completions/mean_length": 1023.21875, + "completions/mean_terminated_length": 974.0, + "completions/min_length": 974.0, + "completions/min_terminated_length": 974.0, + "epoch": 0.10208193418401612, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.1916330918644496e-06, + "loss": 0.0, + "num_tokens": 23393490.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 228 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1012.0, + "completions/mean_length": 1018.34375, + "completions/mean_terminated_length": 933.5, + "completions/min_length": 866.0, + "completions/min_terminated_length": 866.0, + "epoch": 0.10252966196552496, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.177333034714303e-06, + "loss": 0.0, + "num_tokens": 23494888.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 229 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1029773897470338, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.1630150475258813e-06, + "loss": 0.0, + "num_tokens": 23596568.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 230 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 891.0, + "completions/mean_length": 1012.34375, + "completions/mean_terminated_length": 775.3333740234375, + "completions/min_length": 699.0, + "completions/min_terminated_length": 699.0, + "epoch": 0.10342511752854265, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.148679731053252e-06, + "loss": 0.0, + "num_tokens": 23696510.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 231 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 981.0, + "completions/mean_length": 1021.640625, + "completions/mean_terminated_length": 948.5, + "completions/min_length": 916.0, + "completions/min_terminated_length": 916.0, + "epoch": 0.10387284531005149, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.1343276867775805e-06, + "loss": 0.0, + "num_tokens": 23801939.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 232 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 657.0, + "completions/mean_length": 1018.265625, + "completions/mean_terminated_length": 657.0, + "completions/min_length": 657.0, + "completions/min_terminated_length": 657.0, + "epoch": 0.10432057309156033, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.1199595168819043e-06, + "loss": 0.0, + "num_tokens": 23901532.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 233 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10476830087306917, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.105575824225852e-06, + "loss": 0.0, + "num_tokens": 24004644.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 234 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 963.0, + "completions/mean_length": 1017.703125, + "completions/mean_terminated_length": 822.5, + "completions/min_length": 682.0, + "completions/min_terminated_length": 682.0, + "epoch": 0.10521602865457802, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.091177212320363e-06, + "loss": 0.0, + "num_tokens": 24108497.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 235 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 822.0, + "completions/mean_length": 1017.5625, + "completions/mean_terminated_length": 818.0, + "completions/min_length": 814.0, + "completions/min_terminated_length": 814.0, + "epoch": 0.10566375643608686, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.0767642853023538e-06, + "loss": 0.0, + "num_tokens": 24210321.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 236 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1011.0, + "completions/mean_length": 1007.625, + "completions/mean_terminated_length": 874.2857666015625, + "completions/min_length": 660.0, + "completions/min_terminated_length": 660.0, + "epoch": 0.1061114842175957, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.062337647909376e-06, + "loss": 0.0, + "num_tokens": 24313089.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 237 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 935.0, + "completions/mean_length": 1022.609375, + "completions/mean_terminated_length": 935.0, + "completions/min_length": 935.0, + "completions/min_terminated_length": 935.0, + "epoch": 0.10655921199910455, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.04789790545424e-06, + "loss": 0.0, + "num_tokens": 24415908.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 238 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1024.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 1024.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 1024.0, + "epoch": 0.10700693978061339, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.033445663799621e-06, + "loss": 0.0, + "num_tokens": 24520580.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 239 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10745466756212223, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.018981529332633e-06, + "loss": 0.0, + "num_tokens": 24625368.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 240 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10790239534363107, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 3.00450610893939e-06, + "loss": 0.0, + "num_tokens": 24723052.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 241 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10835012312513992, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.9900200099795396e-06, + "loss": 0.0, + "num_tokens": 24829812.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 242 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.10879785090664876, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.9755238402607826e-06, + "loss": 0.0, + "num_tokens": 24933372.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 243 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1020.0, + "completions/mean_length": 1006.78125, + "completions/mean_terminated_length": 748.5, + "completions/min_length": 491.0, + "completions/min_terminated_length": 491.0, + "epoch": 0.1092455786881576, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.961018208013367e-06, + "loss": 0.0, + "num_tokens": 25035482.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 244 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1022.0, + "completions/mean_length": 1019.8125, + "completions/mean_terminated_length": 934.6666870117188, + "completions/min_length": 820.0, + "completions/min_terminated_length": 820.0, + "epoch": 0.10969330646966645, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.9465037218645694e-06, + "loss": 0.0, + "num_tokens": 25136250.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 245 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 898.0, + "completions/mean_length": 1022.03125, + "completions/mean_terminated_length": 898.0, + "completions/min_length": 898.0, + "completions/min_terminated_length": 898.0, + "epoch": 0.11014103425117529, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.9319809908131604e-06, + "loss": 0.0, + "num_tokens": 25239468.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 246 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 767.0, + "completions/mean_length": 989.734375, + "completions/mean_terminated_length": 585.4000244140625, + "completions/min_length": 494.0, + "completions/min_terminated_length": 494.0, + "epoch": 0.11058876203268413, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.917450624203847e-06, + "loss": 0.0, + "num_tokens": 25346935.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 247 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 870.0, + "completions/mean_length": 1015.203125, + "completions/mean_terminated_length": 836.3333740234375, + "completions/min_length": 803.0, + "completions/min_terminated_length": 803.0, + "epoch": 0.11103648981419297, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.9029132317017118e-06, + "loss": 0.0, + "num_tokens": 25443492.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 248 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11148421759570182, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.888369423266629e-06, + "loss": 0.0, + "num_tokens": 25544716.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 249 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11193194537721066, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.8738198091276712e-06, + "loss": 0.0, + "num_tokens": 25646572.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 250 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1123796731587195, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.859264999757509e-06, + "loss": 0.0, + "num_tokens": 25750156.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 251 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11282740094022835, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.8447056058467928e-06, + "loss": 0.0, + "num_tokens": 25853932.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 252 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 998.0, + "completions/mean_length": 1008.46875, + "completions/mean_terminated_length": 899.75, + "completions/min_length": 783.0, + "completions/min_terminated_length": 783.0, + "epoch": 0.11327512872173719, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.830142238278531e-06, + "loss": 0.0, + "num_tokens": 25952230.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 253 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11372285650324603, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.81557550810246e-06, + "loss": 0.0, + "num_tokens": 26061818.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 254 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11417058428475486, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.8010060265094026e-06, + "loss": 0.0, + "num_tokens": 26165614.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 255 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11461831206626372, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.786434404805629e-06, + "loss": 0.0, + "num_tokens": 26266538.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 256 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11506603984777256, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.771861254387199e-06, + "loss": 0.0, + "num_tokens": 26368514.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 257 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1155137676292814, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.7572871867143204e-06, + "loss": 0.0, + "num_tokens": 26472162.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 258 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11596149541079023, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.742712813285681e-06, + "loss": 0.0, + "num_tokens": 26576558.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 259 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 626.0, + "completions/mean_length": 994.25, + "completions/mean_terminated_length": 548.0, + "completions/min_length": 463.0, + "completions/min_terminated_length": 463.0, + "epoch": 0.11640922319229909, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.7281387456128017e-06, + "loss": 0.0, + "num_tokens": 26677778.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 260 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11685695097380792, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.7135655951943716e-06, + "loss": 0.0, + "num_tokens": 26777050.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 261 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 877.0, + "completions/mean_length": 1012.671875, + "completions/mean_terminated_length": 782.3333740234375, + "completions/min_length": 732.0, + "completions/min_terminated_length": 732.0, + "epoch": 0.11730467875531676, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.698993973490598e-06, + "loss": 0.0, + "num_tokens": 26880037.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 262 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1014.0, + "completions/mean_length": 1012.859375, + "completions/mean_terminated_length": 845.75, + "completions/min_length": 479.0, + "completions/min_terminated_length": 479.0, + "epoch": 0.11775240653682562, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.6844244918975416e-06, + "loss": 0.0, + "num_tokens": 26979824.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 263 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 909.0, + "completions/mean_length": 1013.328125, + "completions/mean_terminated_length": 796.3333740234375, + "completions/min_length": 732.0, + "completions/min_terminated_length": 732.0, + "epoch": 0.11820013431833445, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.66985776172147e-06, + "loss": 0.0, + "num_tokens": 27083061.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 264 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 692.0, + "completions/mean_length": 1018.8125, + "completions/mean_terminated_length": 692.0, + "completions/min_length": 692.0, + "completions/min_terminated_length": 692.0, + "epoch": 0.1186478620998433, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.6552943941532088e-06, + "loss": 0.0, + "num_tokens": 27191749.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 265 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11909558988135213, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.6407350002424927e-06, + "loss": 0.0, + "num_tokens": 27295561.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 266 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 851.0, + "completions/mean_length": 1014.59375, + "completions/mean_terminated_length": 723.0, + "completions/min_length": 595.0, + "completions/min_terminated_length": 595.0, + "epoch": 0.11954331766286098, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.626180190872329e-06, + "loss": 0.0, + "num_tokens": 27396955.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 267 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.11999104544436982, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.611630576733372e-06, + "loss": 0.0, + "num_tokens": 27501115.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 268 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 954.0, + "completions/mean_length": 1017.734375, + "completions/mean_terminated_length": 890.3333740234375, + "completions/min_length": 796.0, + "completions/min_terminated_length": 796.0, + "epoch": 0.12043877322587866, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.5970867682982885e-06, + "loss": 0.0, + "num_tokens": 27601478.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 269 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 749.0, + "completions/mean_length": 1003.703125, + "completions/mean_terminated_length": 699.25, + "completions/min_length": 590.0, + "completions/min_terminated_length": 590.0, + "epoch": 0.12088650100738751, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.582549375796154e-06, + "loss": 0.0, + "num_tokens": 27708527.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 270 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1013.0, + "completions/mean_length": 1021.25, + "completions/mean_terminated_length": 936.0, + "completions/min_length": 859.0, + "completions/min_terminated_length": 859.0, + "epoch": 0.12133422878889635, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.568019009186841e-06, + "loss": 0.0, + "num_tokens": 27803367.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 271 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12178195657040519, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.5534962781354317e-06, + "loss": 0.0, + "num_tokens": 27908035.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 272 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1000.0, + "completions/mean_length": 977.375, + "completions/mean_terminated_length": 651.0, + "completions/min_length": 312.0, + "completions/min_terminated_length": 312.0, + "epoch": 0.12222968435191403, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.538981791986634e-06, + "loss": 0.0, + "num_tokens": 28005363.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 273 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 973.0, + "completions/mean_length": 1020.84375, + "completions/mean_terminated_length": 956.6666870117188, + "completions/min_length": 936.0, + "completions/min_terminated_length": 936.0, + "epoch": 0.12267741213342288, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.524476159739218e-06, + "loss": 0.0, + "num_tokens": 28110405.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 274 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12312513991493172, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.5099799900204607e-06, + "loss": 0.0, + "num_tokens": 28217205.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 275 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12357286769644056, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.4954938910606108e-06, + "loss": 0.0, + "num_tokens": 28327329.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 276 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12402059547794941, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.481018470667368e-06, + "loss": 0.0, + "num_tokens": 28433893.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 277 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1021.0, + "completions/mean_length": 1021.328125, + "completions/mean_terminated_length": 967.0, + "completions/min_length": 874.0, + "completions/min_terminated_length": 874.0, + "epoch": 0.12446832325945825, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.4665543362003802e-06, + "loss": 0.0, + "num_tokens": 28537958.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 278 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12491605104096709, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.4521020945457615e-06, + "loss": 0.0, + "num_tokens": 28644242.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 279 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 861.0, + "completions/mean_length": 1014.234375, + "completions/mean_terminated_length": 815.6666870117188, + "completions/min_length": 762.0, + "completions/min_terminated_length": 762.0, + "epoch": 0.12536377882247593, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.4376623520906255e-06, + "loss": 0.0, + "num_tokens": 28747173.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 280 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 978.0, + "completions/mean_length": 1023.28125, + "completions/mean_terminated_length": 978.0, + "completions/min_length": 978.0, + "completions/min_terminated_length": 978.0, + "epoch": 0.12581150660398477, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.4232357146976478e-06, + "loss": 0.0, + "num_tokens": 28846335.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 281 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 981.0, + "completions/mean_length": 984.140625, + "completions/mean_terminated_length": 705.125, + "completions/min_length": 397.0, + "completions/min_terminated_length": 397.0, + "epoch": 0.1262592343854936, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.408822787679637e-06, + "loss": 0.0, + "num_tokens": 28944584.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 282 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12670696216700247, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.3944241757741475e-06, + "loss": 0.0, + "num_tokens": 29048592.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 283 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 996.0, + "completions/mean_length": 1022.234375, + "completions/mean_terminated_length": 986.3333740234375, + "completions/min_length": 980.0, + "completions/min_terminated_length": 980.0, + "epoch": 0.1271546899485113, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.380040483118097e-06, + "loss": 0.0, + "num_tokens": 29146015.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 284 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12760241773002015, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.365672313222419e-06, + "loss": 0.0, + "num_tokens": 29254239.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 285 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 945.0, + "completions/mean_length": 995.203125, + "completions/mean_terminated_length": 793.625, + "completions/min_length": 618.0, + "completions/min_terminated_length": 618.0, + "epoch": 0.128050145511529, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.351320268946749e-06, + "loss": 0.0, + "num_tokens": 29356836.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 286 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.12849787329303783, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.336984952474119e-06, + "loss": 0.0, + "num_tokens": 29459356.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 287 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 993.0, + "completions/mean_length": 1023.515625, + "completions/mean_terminated_length": 993.0, + "completions/min_length": 993.0, + "completions/min_terminated_length": 993.0, + "epoch": 0.12894560107454667, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.322666965285697e-06, + "loss": 0.0, + "num_tokens": 29563537.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 288 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1293933288560555, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.3083669081355507e-06, + "loss": 0.0, + "num_tokens": 29665269.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 289 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 933.0, + "completions/mean_length": 1019.5, + "completions/mean_terminated_length": 880.0, + "completions/min_length": 827.0, + "completions/min_terminated_length": 827.0, + "epoch": 0.12984105663756437, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.2940853810254377e-06, + "loss": 0.0, + "num_tokens": 29767637.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 290 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 926.0, + "completions/mean_length": 1022.46875, + "completions/mean_terminated_length": 926.0, + "completions/min_length": 926.0, + "completions/min_terminated_length": 926.0, + "epoch": 0.1302887844190732, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.2798229831796313e-06, + "loss": 0.0, + "num_tokens": 29874343.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 291 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13073651220058205, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.2655803130197816e-06, + "loss": 0.0, + "num_tokens": 29972583.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 292 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 723.0, + "completions/mean_length": 1019.296875, + "completions/mean_terminated_length": 723.0, + "completions/min_length": 723.0, + "completions/min_terminated_length": 723.0, + "epoch": 0.1311842399820909, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.2513579681398034e-06, + "loss": 0.0, + "num_tokens": 30071058.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 293 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13163196776359973, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.237156545280803e-06, + "loss": 0.0, + "num_tokens": 30169818.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 294 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13207969554510857, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.2229766403060403e-06, + "loss": 0.0, + "num_tokens": 30276070.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 295 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 967.0, + "completions/mean_length": 979.875, + "completions/mean_terminated_length": 671.0, + "completions/min_length": 405.0, + "completions/min_terminated_length": 405.0, + "epoch": 0.1325274233266174, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.2088188481759305e-06, + "loss": 0.0, + "num_tokens": 30372462.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 296 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 947.0, + "completions/mean_length": 1019.484375, + "completions/mean_terminated_length": 879.5, + "completions/min_length": 812.0, + "completions/min_terminated_length": 812.0, + "epoch": 0.13297515110812627, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.194683762923073e-06, + "loss": 0.0, + "num_tokens": 30474953.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 297 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1334228788896351, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.1805719776273387e-06, + "loss": 0.0, + "num_tokens": 30577777.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 298 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 959.0, + "completions/mean_length": 1022.984375, + "completions/mean_terminated_length": 959.0, + "completions/min_length": 959.0, + "completions/min_terminated_length": 959.0, + "epoch": 0.13387060667114395, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.166484084390974e-06, + "loss": 0.0, + "num_tokens": 30678732.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 299 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 612.0, + "completions/mean_length": 986.109375, + "completions/mean_terminated_length": 539.0, + "completions/min_length": 484.0, + "completions/min_terminated_length": 484.0, + "epoch": 0.1343183344526528, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.1524206743137636e-06, + "loss": 0.0, + "num_tokens": 30784915.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 300 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13476606223416163, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.1383823374682287e-06, + "loss": 0.0, + "num_tokens": 30886183.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 301 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13521379001567047, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.124369662874868e-06, + "loss": 0.0, + "num_tokens": 30992427.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 302 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1356615177971793, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.110383238477441e-06, + "loss": 0.0, + "num_tokens": 31093823.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 303 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13610924557868817, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.096423651118305e-06, + "loss": 0.0, + "num_tokens": 31195579.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 304 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 794.0, + "completions/mean_length": 1014.78125, + "completions/mean_terminated_length": 729.0, + "completions/min_length": 664.0, + "completions/min_terminated_length": 664.0, + "epoch": 0.136556973360197, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.082491486513788e-06, + "loss": 0.0, + "num_tokens": 31297953.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 305 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 757.0, + "completions/mean_length": 1019.828125, + "completions/mean_terminated_length": 757.0, + "completions/min_length": 757.0, + "completions/min_terminated_length": 757.0, + "epoch": 0.13700470114170585, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.0685873292296116e-06, + "loss": 0.0, + "num_tokens": 31398390.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 306 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1374524289232147, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.054711762656369e-06, + "loss": 0.0, + "num_tokens": 31496858.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 307 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.13790015670472353, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.040865368985044e-06, + "loss": 0.0, + "num_tokens": 31601962.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 308 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 844.0, + "completions/mean_length": 1021.1875, + "completions/mean_terminated_length": 844.0, + "completions/min_length": 844.0, + "completions/min_terminated_length": 844.0, + "epoch": 0.13834788448623236, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.027048729182583e-06, + "loss": 0.0, + "num_tokens": 31701906.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 309 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 940.0, + "completions/mean_length": 1015.03125, + "completions/mean_terminated_length": 880.5, + "completions/min_length": 841.0, + "completions/min_terminated_length": 841.0, + "epoch": 0.1387956122677412, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 2.0132624229675205e-06, + "loss": 0.0, + "num_tokens": 31804000.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 310 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 568.0, + "completions/mean_length": 1009.078125, + "completions/mean_terminated_length": 546.5, + "completions/min_length": 525.0, + "completions/min_terminated_length": 525.0, + "epoch": 0.13924334004925007, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.9995070287856546e-06, + "loss": 0.0, + "num_tokens": 31907121.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 311 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1396910678307589, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.985783123785774e-06, + "loss": 0.0, + "num_tokens": 32010077.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 312 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14013879561226775, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.9720912837954486e-06, + "loss": 0.0, + "num_tokens": 32113957.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 313 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14058652339377659, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.958432083296862e-06, + "loss": 0.0, + "num_tokens": 32217953.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 314 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 896.0, + "completions/mean_length": 1008.53125, + "completions/mean_terminated_length": 776.5, + "completions/min_length": 674.0, + "completions/min_terminated_length": 674.0, + "epoch": 0.14103425117528542, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.9448060954027093e-06, + "loss": 0.0, + "num_tokens": 32320719.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 315 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 870.0, + "completions/mean_length": 1008.828125, + "completions/mean_terminated_length": 700.3333740234375, + "completions/min_length": 497.0, + "completions/min_terminated_length": 497.0, + "epoch": 0.14148197895679426, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.931213891832153e-06, + "loss": 0.0, + "num_tokens": 32429972.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 316 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 918.0, + "completions/mean_length": 1008.6875, + "completions/mean_terminated_length": 779.0, + "completions/min_length": 612.0, + "completions/min_terminated_length": 612.0, + "epoch": 0.1419297067383031, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.9176560428868336e-06, + "loss": 0.0, + "num_tokens": 32528964.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 317 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14237743451981194, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.9041331174269373e-06, + "loss": 0.0, + "num_tokens": 32634952.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 318 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 988.0, + "completions/mean_length": 988.28125, + "completions/mean_terminated_length": 697.4285888671875, + "completions/min_length": 434.0, + "completions/min_terminated_length": 434.0, + "epoch": 0.1428251623013208, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.8906456828473341e-06, + "loss": 0.0, + "num_tokens": 32731842.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 319 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1008.0, + "completions/mean_length": 1008.109375, + "completions/mean_terminated_length": 854.5, + "completions/min_length": 600.0, + "completions/min_terminated_length": 600.0, + "epoch": 0.14327289008282965, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.8771943050537656e-06, + "loss": 0.0, + "num_tokens": 32835205.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 320 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 968.0, + "completions/mean_length": 1004.28125, + "completions/mean_terminated_length": 771.6000366210938, + "completions/min_length": 657.0, + "completions/min_terminated_length": 657.0, + "epoch": 0.14372061786433848, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.8637795484391046e-06, + "loss": 0.0, + "num_tokens": 32934083.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 321 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 688.0, + "completions/mean_length": 1013.015625, + "completions/mean_terminated_length": 672.5, + "completions/min_length": 657.0, + "completions/min_terminated_length": 657.0, + "epoch": 0.14416834564584732, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.8504019758596698e-06, + "loss": 0.0, + "num_tokens": 33035336.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 322 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14461607342735616, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.8370621486116163e-06, + "loss": 0.0, + "num_tokens": 33141652.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 323 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.145063801208865, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.823760626407377e-06, + "loss": 0.0, + "num_tokens": 33248740.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 324 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14551152899037384, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.8104979673521838e-06, + "loss": 0.0, + "num_tokens": 33349932.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 325 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1024.0, + "completions/mean_length": 1023.890625, + "completions/mean_terminated_length": 1020.5, + "completions/min_length": 1017.0, + "completions/min_terminated_length": 1017.0, + "epoch": 0.1459592567718827, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.7972747279206482e-06, + "loss": 0.0, + "num_tokens": 33455625.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 326 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14640698455339154, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.7840914629334122e-06, + "loss": 0.0, + "num_tokens": 33560957.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 327 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 942.0, + "completions/mean_length": 1001.1875, + "completions/mean_terminated_length": 780.6666870117188, + "completions/min_length": 589.0, + "completions/min_terminated_length": 589.0, + "epoch": 0.14685471233490038, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.7709487255338731e-06, + "loss": 0.0, + "num_tokens": 33657329.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 328 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14730244011640922, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.7578470671649684e-06, + "loss": 0.0, + "num_tokens": 33762765.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 329 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14775016789791806, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.744787037546045e-06, + "loss": 0.0, + "num_tokens": 33870397.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 330 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 720.0, + "completions/mean_length": 996.984375, + "completions/mean_terminated_length": 591.75, + "completions/min_length": 414.0, + "completions/min_terminated_length": 414.0, + "epoch": 0.1481978956794269, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.731769184649788e-06, + "loss": 0.0, + "num_tokens": 33970628.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 331 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14864562346093574, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.7187940546792325e-06, + "loss": 0.0, + "num_tokens": 34073492.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 332 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1490933512424446, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.7058621920448465e-06, + "loss": 0.0, + "num_tokens": 34176724.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 333 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14954107902395344, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6929741393416855e-06, + "loss": 0.0, + "num_tokens": 34283612.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 334 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.14998880680546228, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6801304373266286e-06, + "loss": 0.0, + "num_tokens": 34383576.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 335 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.15043653458697112, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.667331624895689e-06, + "loss": 0.0, + "num_tokens": 34484808.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 336 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.15088426236847996, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6545782390614037e-06, + "loss": 0.0, + "num_tokens": 34588276.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 337 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1513319901499888, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6418708149302992e-06, + "loss": 0.0, + "num_tokens": 34695028.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 338 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 974.0, + "completions/mean_length": 1023.21875, + "completions/mean_terminated_length": 974.0, + "completions/min_length": 974.0, + "completions/min_terminated_length": 974.0, + "epoch": 0.15177971793149764, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6292098856804423e-06, + "loss": 0.0, + "num_tokens": 34793438.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 339 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1000.0, + "completions/mean_length": 1020.125, + "completions/mean_terminated_length": 900.0, + "completions/min_length": 800.0, + "completions/min_terminated_length": 800.0, + "epoch": 0.1522274457130065, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.6165959825390661e-06, + "loss": 0.0, + "num_tokens": 34898970.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 340 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 919.0, + "completions/mean_length": 1020.578125, + "completions/mean_terminated_length": 914.5, + "completions/min_length": 910.0, + "completions/min_terminated_length": 910.0, + "epoch": 0.15267517349451534, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.604029634760284e-06, + "loss": 0.0, + "num_tokens": 35003843.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 341 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 890.0, + "completions/mean_length": 996.171875, + "completions/mean_terminated_length": 727.1666870117188, + "completions/min_length": 643.0, + "completions/min_terminated_length": 643.0, + "epoch": 0.15312290127602418, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.59151136960288e-06, + "loss": 0.0, + "num_tokens": 35098370.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 342 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.15357062905753302, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.5790417123081903e-06, + "loss": 0.0, + "num_tokens": 35200326.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 343 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.15401835683904186, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.5666211860780583e-06, + "loss": 0.0, + "num_tokens": 35303494.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 344 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 897.0, + "completions/mean_length": 1015.765625, + "completions/mean_terminated_length": 848.3333740234375, + "completions/min_length": 788.0, + "completions/min_terminated_length": 788.0, + "epoch": 0.1544660846205507, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.5542503120528918e-06, + "loss": 0.0, + "num_tokens": 35399051.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 345 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.15491381240205954, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.5419296092897866e-06, + "loss": 0.0, + "num_tokens": 35501039.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 346 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1553615401835684, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.529659594740755e-06, + "loss": 0.0, + "num_tokens": 35602571.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 347 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 463.0, + "completions/mean_length": 983.828125, + "completions/mean_terminated_length": 381.25, + "completions/min_length": 316.0, + "completions/min_terminated_length": 316.0, + "epoch": 0.15580926796507724, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.5174407832310338e-06, + "loss": 0.0, + "num_tokens": 35704368.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 348 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 829.0, + "completions/mean_length": 1020.953125, + "completions/mean_terminated_length": 829.0, + "completions/min_length": 829.0, + "completions/min_terminated_length": 829.0, + "epoch": 0.15625699574658608, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.5052736874374815e-06, + "loss": 0.0, + "num_tokens": 35810209.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 349 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 690.0, + "completions/mean_length": 1000.671875, + "completions/mean_terminated_length": 650.75, + "completions/min_length": 614.0, + "completions/min_terminated_length": 614.0, + "epoch": 0.15670472352809492, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.4931588178670695e-06, + "loss": 0.0, + "num_tokens": 35909008.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 350 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1006.0, + "completions/mean_length": 1012.375, + "completions/mean_terminated_length": 776.0, + "completions/min_length": 572.0, + "completions/min_terminated_length": 572.0, + "epoch": 0.15715245130960376, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.4810966828354605e-06, + "loss": 0.0, + "num_tokens": 36009144.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 351 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1576001790911126, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.469087788445684e-06, + "loss": 0.0, + "num_tokens": 36113352.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 352 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 819.0, + "completions/mean_length": 995.609375, + "completions/mean_terminated_length": 569.75, + "completions/min_length": 376.0, + "completions/min_terminated_length": 376.0, + "epoch": 0.15804790687262144, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.4571326385668965e-06, + "loss": 0.0, + "num_tokens": 36213891.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 353 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 992.0, + "completions/mean_length": 1020.28125, + "completions/mean_terminated_length": 944.6666870117188, + "completions/min_length": 912.0, + "completions/min_terminated_length": 912.0, + "epoch": 0.1584956346541303, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.4452317348132434e-06, + "loss": 0.0, + "num_tokens": 36316329.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 354 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.15894336243563914, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.4333855765228104e-06, + "loss": 0.0, + "num_tokens": 36421637.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 355 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1017.0, + "completions/mean_length": 1023.890625, + "completions/mean_terminated_length": 1017.0, + "completions/min_length": 1017.0, + "completions/min_terminated_length": 1017.0, + "epoch": 0.15939109021714798, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.421594660736675e-06, + "loss": 0.0, + "num_tokens": 36519866.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 356 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 794.0, + "completions/mean_length": 988.203125, + "completions/mean_terminated_length": 565.7999877929688, + "completions/min_length": 433.0, + "completions/min_terminated_length": 433.0, + "epoch": 0.15983881799865682, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.4098594821780476e-06, + "loss": 0.0, + "num_tokens": 36618291.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 357 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.16028654578016566, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3981805332315174e-06, + "loss": 0.0, + "num_tokens": 36717631.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 358 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1607342735616745, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3865583039223929e-06, + "loss": 0.0, + "num_tokens": 36823451.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 359 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 990.0, + "completions/mean_length": 1021.671875, + "completions/mean_terminated_length": 949.5, + "completions/min_length": 909.0, + "completions/min_terminated_length": 909.0, + "epoch": 0.16118200134318333, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.374993281896137e-06, + "loss": 0.0, + "num_tokens": 36928134.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 360 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1616297291246922, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3634859523979134e-06, + "loss": 0.0, + "num_tokens": 37031606.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 361 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 993.0, + "completions/mean_length": 1021.4375, + "completions/mean_terminated_length": 969.3333740234375, + "completions/min_length": 948.0, + "completions/min_terminated_length": 948.0, + "epoch": 0.16207745690620104, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3520367982522208e-06, + "loss": 0.0, + "num_tokens": 37132406.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 362 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.16252518468770988, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3406462998426358e-06, + "loss": 0.0, + "num_tokens": 37239258.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 363 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.16297291246921872, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3293149350916595e-06, + "loss": 0.0, + "num_tokens": 37341606.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 364 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.16342064025072756, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3180431794406623e-06, + "loss": 0.0, + "num_tokens": 37444194.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 365 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1020.0, + "completions/mean_length": 1019.765625, + "completions/mean_terminated_length": 888.5, + "completions/min_length": 757.0, + "completions/min_terminated_length": 757.0, + "epoch": 0.1638683680322364, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.3068315058299358e-06, + "loss": 0.0, + "num_tokens": 37546959.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 366 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 775.0, + "completions/mean_length": 1013.40625, + "completions/mean_terminated_length": 685.0, + "completions/min_length": 595.0, + "completions/min_terminated_length": 595.0, + "epoch": 0.16431609581374523, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2956803846788503e-06, + "loss": 0.0, + "num_tokens": 37650985.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 367 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.16476382359525407, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.284590283866116e-06, + "loss": 0.0, + "num_tokens": 37755533.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 368 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 737.0, + "completions/mean_length": 1019.515625, + "completions/mean_terminated_length": 737.0, + "completions/min_length": 737.0, + "completions/min_terminated_length": 737.0, + "epoch": 0.16521155137676294, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2735616687101518e-06, + "loss": 0.0, + "num_tokens": 37858578.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 369 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.16565927915827178, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2625950019495614e-06, + "loss": 0.0, + "num_tokens": 37963654.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 370 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 974.0, + "completions/mean_length": 1004.90625, + "completions/mean_terminated_length": 718.5, + "completions/min_length": 524.0, + "completions/min_terminated_length": 524.0, + "epoch": 0.16610700693978062, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.251690743723718e-06, + "loss": 0.0, + "num_tokens": 38066624.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 371 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1019.0, + "completions/mean_length": 1007.796875, + "completions/mean_terminated_length": 875.857177734375, + "completions/min_length": 719.0, + "completions/min_terminated_length": 719.0, + "epoch": 0.16655473472128945, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2408493515534581e-06, + "loss": 0.0, + "num_tokens": 38166811.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 372 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1670024625027983, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2300712803218834e-06, + "loss": 0.0, + "num_tokens": 38264455.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 373 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 569.0, + "completions/mean_length": 952.8125, + "completions/mean_terminated_length": 454.5, + "completions/min_length": 383.0, + "completions/min_terminated_length": 383.0, + "epoch": 0.16745019028430713, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2193569822552772e-06, + "loss": 0.0, + "num_tokens": 38365935.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 374 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1004.0, + "completions/mean_length": 1018.84375, + "completions/mean_terminated_length": 914.0, + "completions/min_length": 842.0, + "completions/min_terminated_length": 842.0, + "epoch": 0.16789791806581597, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.2087069069041268e-06, + "loss": 0.0, + "num_tokens": 38468541.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 375 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 780.0, + "completions/mean_length": 1020.1875, + "completions/mean_terminated_length": 780.0, + "completions/min_length": 780.0, + "completions/min_terminated_length": 780.0, + "epoch": 0.16834564584732484, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1981215011242654e-06, + "loss": 0.0, + "num_tokens": 38571893.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 376 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 925.0, + "completions/mean_length": 989.0625, + "completions/mean_terminated_length": 651.3333740234375, + "completions/min_length": 483.0, + "completions/min_terminated_length": 483.0, + "epoch": 0.16879337362883368, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1876012090581184e-06, + "loss": 0.0, + "num_tokens": 38674301.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 377 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 849.0, + "completions/mean_length": 1007.328125, + "completions/mean_terminated_length": 757.25, + "completions/min_length": 644.0, + "completions/min_terminated_length": 644.0, + "epoch": 0.16924110141034251, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.177146472116071e-06, + "loss": 0.0, + "num_tokens": 38778514.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 378 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 917.0, + "completions/mean_length": 1022.328125, + "completions/mean_terminated_length": 917.0, + "completions/min_length": 917.0, + "completions/min_terminated_length": 917.0, + "epoch": 0.16968882919185135, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1667577289579462e-06, + "loss": 0.0, + "num_tokens": 38881743.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 379 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1701365569733602, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1564354154746007e-06, + "loss": 0.0, + "num_tokens": 38983243.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 380 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17058428475486903, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.146179964769635e-06, + "loss": 0.0, + "num_tokens": 39088119.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 381 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17103201253637787, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1359918071412195e-06, + "loss": 0.0, + "num_tokens": 39189363.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 382 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 980.0, + "completions/mean_length": 1007.5625, + "completions/mean_terminated_length": 761.0, + "completions/min_length": 475.0, + "completions/min_terminated_length": 475.0, + "epoch": 0.17147974031788674, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1258713700640456e-06, + "loss": 0.0, + "num_tokens": 39290403.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 383 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 703.0, + "completions/mean_length": 1006.03125, + "completions/mean_terminated_length": 640.6666870117188, + "completions/min_length": 575.0, + "completions/min_terminated_length": 575.0, + "epoch": 0.17192746809939558, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.115819078171383e-06, + "loss": 0.0, + "num_tokens": 39393673.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 384 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 632.0, + "completions/mean_length": 953.75, + "completions/mean_terminated_length": 462.0, + "completions/min_length": 401.0, + "completions/min_terminated_length": 401.0, + "epoch": 0.1723751958809044, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.1058353532372667e-06, + "loss": 0.0, + "num_tokens": 39487265.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 385 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17282292366241325, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0959206141587998e-06, + "loss": 0.0, + "num_tokens": 39590277.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 386 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 808.0, + "completions/mean_length": 1020.625, + "completions/mean_terminated_length": 808.0, + "completions/min_length": 808.0, + "completions/min_terminated_length": 808.0, + "epoch": 0.1732706514439221, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0860752769385766e-06, + "loss": 0.0, + "num_tokens": 39691493.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 387 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 935.0, + "completions/mean_length": 1022.609375, + "completions/mean_terminated_length": 935.0, + "completions/min_length": 935.0, + "completions/min_terminated_length": 935.0, + "epoch": 0.17371837922543093, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0762997546672279e-06, + "loss": 0.0, + "num_tokens": 39794420.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 388 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 645.0, + "completions/mean_length": 996.765625, + "completions/mean_terminated_length": 588.25, + "completions/min_length": 451.0, + "completions/min_terminated_length": 451.0, + "epoch": 0.17416610700693977, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0665944575060914e-06, + "loss": 0.0, + "num_tokens": 39891217.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 389 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 880.0, + "completions/mean_length": 1021.75, + "completions/mean_terminated_length": 880.0, + "completions/min_length": 880.0, + "completions/min_terminated_length": 880.0, + "epoch": 0.17461383478844864, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.056959792669997e-06, + "loss": 0.0, + "num_tokens": 39993145.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 390 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17506156256995747, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0473961644101856e-06, + "loss": 0.0, + "num_tokens": 40097029.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 391 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 885.0, + "completions/mean_length": 1018.765625, + "completions/mean_terminated_length": 856.5, + "completions/min_length": 828.0, + "completions/min_terminated_length": 828.0, + "epoch": 0.1755092903514663, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.037903973997345e-06, + "loss": 0.0, + "num_tokens": 40197714.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 392 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 982.0, + "completions/mean_length": 1023.34375, + "completions/mean_terminated_length": 982.0, + "completions/min_length": 982.0, + "completions/min_terminated_length": 982.0, + "epoch": 0.17595701813297515, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0284836197047737e-06, + "loss": 0.0, + "num_tokens": 40304304.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 393 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.176404745914484, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0191354967916712e-06, + "loss": 0.0, + "num_tokens": 40406180.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 394 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 961.0, + "completions/mean_length": 1019.171875, + "completions/mean_terminated_length": 921.0, + "completions/min_length": 844.0, + "completions/min_terminated_length": 844.0, + "epoch": 0.17685247369599283, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0098599974865515e-06, + "loss": 0.0, + "num_tokens": 40507759.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 395 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17730020147750167, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 1.0006575109707898e-06, + "loss": 0.0, + "num_tokens": 40611735.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 396 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17774792925901053, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.915284233622877e-07, + "loss": 0.0, + "num_tokens": 40718755.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 397 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 846.0, + "completions/mean_length": 1014.90625, + "completions/mean_terminated_length": 733.0, + "completions/min_length": 620.0, + "completions/min_terminated_length": 620.0, + "epoch": 0.17819565704051937, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.824731176992796e-07, + "loss": 0.0, + "num_tokens": 40815885.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 398 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 790.0, + "completions/mean_length": 981.421875, + "completions/mean_terminated_length": 569.8333740234375, + "completions/min_length": 392.0, + "completions/min_terminated_length": 392.0, + "epoch": 0.1786433848220282, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.734919739242543e-07, + "loss": 0.0, + "num_tokens": 40910204.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 399 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 530.0, + "completions/mean_length": 984.65625, + "completions/mean_terminated_length": 394.5, + "completions/min_length": 263.0, + "completions/min_terminated_length": 263.0, + "epoch": 0.17909111260353705, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.645853688680177e-07, + "loss": 0.0, + "num_tokens": 41016782.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 400 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1795388403850459, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.557536762338786e-07, + "loss": 0.0, + "num_tokens": 41114610.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 401 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.17998656816655473, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.46997266581973e-07, + "loss": 0.0, + "num_tokens": 41221318.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 402 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 987.0, + "completions/mean_length": 987.71875, + "completions/mean_terminated_length": 766.0, + "completions/min_length": 628.0, + "completions/min_terminated_length": 628.0, + "epoch": 0.18043429594806357, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.383165073137115e-07, + "loss": 0.0, + "num_tokens": 41317648.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 403 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18088202372957243, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.297117626563687e-07, + "loss": 0.0, + "num_tokens": 41425452.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 404 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 961.0, + "completions/mean_length": 991.46875, + "completions/mean_terminated_length": 726.5714721679688, + "completions/min_length": 500.0, + "completions/min_terminated_length": 500.0, + "epoch": 0.18132975151108127, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.211833936477957e-07, + "loss": 0.0, + "num_tokens": 41526374.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 405 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 580.0, + "completions/mean_length": 988.609375, + "completions/mean_terminated_length": 457.75, + "completions/min_length": 328.0, + "completions/min_terminated_length": 328.0, + "epoch": 0.1817774792925901, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.127317581212753e-07, + "loss": 0.0, + "num_tokens": 41622185.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 406 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 944.0, + "completions/mean_length": 1014.171875, + "completions/mean_terminated_length": 814.3333740234375, + "completions/min_length": 616.0, + "completions/min_terminated_length": 616.0, + "epoch": 0.18222520707409895, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 9.043572106905084e-07, + "loss": 0.0, + "num_tokens": 41727552.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 407 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 997.0, + "completions/mean_length": 1012.796875, + "completions/mean_terminated_length": 785.0, + "completions/min_length": 544.0, + "completions/min_terminated_length": 544.0, + "epoch": 0.1826729348556078, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.960601027347321e-07, + "loss": 0.0, + "num_tokens": 41830279.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 408 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18312066263711663, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.878407823839788e-07, + "loss": 0.0, + "num_tokens": 41940283.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 409 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18356839041862547, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.796995945044689e-07, + "loss": 0.0, + "num_tokens": 42044591.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 410 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18401611820013433, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.716368806841405e-07, + "loss": 0.0, + "num_tokens": 42149263.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 411 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18446384598164317, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.636529792183171e-07, + "loss": 0.0, + "num_tokens": 42251307.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 412 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 903.0, + "completions/mean_length": 1011.21875, + "completions/mean_terminated_length": 819.5, + "completions/min_length": 724.0, + "completions/min_terminated_length": 724.0, + "epoch": 0.184911573763152, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.557482250955144e-07, + "loss": 0.0, + "num_tokens": 42352825.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 413 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18535930154466085, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.479229499833844e-07, + "loss": 0.0, + "num_tokens": 42453869.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 414 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1015.0, + "completions/mean_length": 1022.125, + "completions/mean_terminated_length": 984.0, + "completions/min_length": 931.0, + "completions/min_terminated_length": 931.0, + "epoch": 0.1858070293261697, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.401774822147976e-07, + "loss": 0.0, + "num_tokens": 42553773.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 415 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18625475710767853, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.325121467740695e-07, + "loss": 0.0, + "num_tokens": 42660077.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 416 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18670248488918736, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.249272652833226e-07, + "loss": 0.0, + "num_tokens": 42765177.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 417 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 945.0, + "completions/mean_length": 988.828125, + "completions/mean_terminated_length": 573.7999877929688, + "completions/min_length": 369.0, + "completions/min_terminated_length": 369.0, + "epoch": 0.1871502126706962, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.174231559889931e-07, + "loss": 0.0, + "num_tokens": 42861954.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 418 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 931.0, + "completions/mean_length": 1009.609375, + "completions/mean_terminated_length": 793.75, + "completions/min_length": 560.0, + "completions/min_terminated_length": 560.0, + "epoch": 0.18759794045220507, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.100001337484787e-07, + "loss": 0.0, + "num_tokens": 42968361.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 419 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1020.0, + "completions/mean_length": 1009.8125, + "completions/mean_terminated_length": 894.2857666015625, + "completions/min_length": 777.0, + "completions/min_terminated_length": 777.0, + "epoch": 0.1880456682337139, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 8.026585100169251e-07, + "loss": 0.0, + "num_tokens": 43070081.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 420 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 925.0, + "completions/mean_length": 1014.78125, + "completions/mean_terminated_length": 876.5, + "completions/min_length": 830.0, + "completions/min_terminated_length": 830.0, + "epoch": 0.18849339601522275, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.953985928341601e-07, + "loss": 0.0, + "num_tokens": 43177323.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 421 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18894112379673159, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.882206868117693e-07, + "loss": 0.0, + "num_tokens": 43279723.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 422 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.125, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 984.0, + "completions/mean_length": 994.53125, + "completions/mean_terminated_length": 754.5714721679688, + "completions/min_length": 537.0, + "completions/min_terminated_length": 537.0, + "epoch": 0.18938885157824042, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.81125093120313e-07, + "loss": 0.0, + "num_tokens": 43383901.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 423 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.18983657935974926, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.741121094766916e-07, + "loss": 0.0, + "num_tokens": 43486565.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 424 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1016.0, + "completions/mean_length": 1013.09375, + "completions/mean_terminated_length": 849.5, + "completions/min_length": 684.0, + "completions/min_terminated_length": 684.0, + "epoch": 0.1902843071412581, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.671820301316532e-07, + "loss": 0.0, + "num_tokens": 43589287.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 425 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 947.0, + "completions/mean_length": 1018.59375, + "completions/mean_terminated_length": 851.0, + "completions/min_length": 755.0, + "completions/min_terminated_length": 755.0, + "epoch": 0.19073203492276697, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.603351458574474e-07, + "loss": 0.0, + "num_tokens": 43696573.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 426 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1911797627042758, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.535717439356255e-07, + "loss": 0.0, + "num_tokens": 43802765.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 427 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 947.0, + "completions/mean_length": 991.453125, + "completions/mean_terminated_length": 763.625, + "completions/min_length": 601.0, + "completions/min_terminated_length": 601.0, + "epoch": 0.19162749048578465, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.46892108144986e-07, + "loss": 0.0, + "num_tokens": 43905242.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 428 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 573.0, + "completions/mean_length": 994.59375, + "completions/mean_terminated_length": 553.5, + "completions/min_length": 525.0, + "completions/min_terminated_length": 525.0, + "epoch": 0.19207521826729348, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.402965187496697e-07, + "loss": 0.0, + "num_tokens": 44003540.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 429 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 889.0, + "completions/mean_length": 1001.203125, + "completions/mean_terminated_length": 732.2000122070312, + "completions/min_length": 581.0, + "completions/min_terminated_length": 581.0, + "epoch": 0.19252294604880232, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.337852524873974e-07, + "loss": 0.0, + "num_tokens": 44101749.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 430 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 594.0, + "completions/mean_length": 1017.28125, + "completions/mean_terminated_length": 594.0, + "completions/min_length": 594.0, + "completions/min_terminated_length": 594.0, + "epoch": 0.19297067383031116, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.273585825578608e-07, + "loss": 0.0, + "num_tokens": 44198963.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 431 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 943.0, + "completions/mean_length": 1014.296875, + "completions/mean_terminated_length": 817.0, + "completions/min_length": 576.0, + "completions/min_terminated_length": 576.0, + "epoch": 0.19341840161182, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.21016778611259e-07, + "loss": 0.0, + "num_tokens": 44301398.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 432 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.19386612939332887, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.147601067369835e-07, + "loss": 0.0, + "num_tokens": 44408170.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 433 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1943138571748377, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.085888294524561e-07, + "loss": 0.0, + "num_tokens": 44507138.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 434 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 774.0, + "completions/mean_length": 1013.984375, + "completions/mean_terminated_length": 703.5, + "completions/min_length": 633.0, + "completions/min_terminated_length": 633.0, + "epoch": 0.19476158495634655, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 7.025032056921117e-07, + "loss": 0.0, + "num_tokens": 44606301.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 435 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 991.0, + "completions/mean_length": 1023.484375, + "completions/mean_terminated_length": 991.0, + "completions/min_length": 991.0, + "completions/min_terminated_length": 991.0, + "epoch": 0.19520931273785538, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.965034907965349e-07, + "loss": 0.0, + "num_tokens": 44709500.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 436 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 993.0, + "completions/mean_length": 1016.859375, + "completions/mean_terminated_length": 871.6666870117188, + "completions/min_length": 660.0, + "completions/min_terminated_length": 660.0, + "epoch": 0.19565704051936422, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.905899365017462e-07, + "loss": 0.0, + "num_tokens": 44816479.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 437 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1017.0, + "completions/mean_length": 1002.140625, + "completions/mean_terminated_length": 674.25, + "completions/min_length": 541.0, + "completions/min_terminated_length": 541.0, + "epoch": 0.19610476830087306, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.847627909286409e-07, + "loss": 0.0, + "num_tokens": 44920648.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 438 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.1965524960823819, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.790222985725761e-07, + "loss": 0.0, + "num_tokens": 45027828.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 439 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 578.0, + "completions/mean_length": 993.578125, + "completions/mean_terminated_length": 537.25, + "completions/min_length": 461.0, + "completions/min_terminated_length": 461.0, + "epoch": 0.19700022386389077, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.733687002931141e-07, + "loss": 0.0, + "num_tokens": 45132461.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 440 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1013.0, + "completions/mean_length": 998.71875, + "completions/mean_terminated_length": 821.75, + "completions/min_length": 603.0, + "completions/min_terminated_length": 603.0, + "epoch": 0.1974479516453996, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.678022333039158e-07, + "loss": 0.0, + "num_tokens": 45230299.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 441 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 944.0, + "completions/mean_length": 1019.65625, + "completions/mean_terminated_length": 885.0, + "completions/min_length": 826.0, + "completions/min_terminated_length": 826.0, + "epoch": 0.19789567942690844, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.623231311627876e-07, + "loss": 0.0, + "num_tokens": 45329905.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 442 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.19834340720841728, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.569316237618811e-07, + "loss": 0.0, + "num_tokens": 45435929.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 443 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.19879113498992612, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.516279373180499e-07, + "loss": 0.0, + "num_tokens": 45531893.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 444 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.25, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 861.0, + "completions/mean_length": 994.984375, + "completions/mean_terminated_length": 714.5, + "completions/min_length": 649.0, + "completions/min_terminated_length": 649.0, + "epoch": 0.19923886277143496, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.464122943633543e-07, + "loss": 0.0, + "num_tokens": 45629596.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 445 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 971.0, + "completions/mean_length": 1009.28125, + "completions/mean_terminated_length": 788.5, + "completions/min_length": 546.0, + "completions/min_terminated_length": 546.0, + "epoch": 0.1996865905529438, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.412849137357271e-07, + "loss": 0.0, + "num_tokens": 45734158.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 446 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20013431833445267, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.3624601056979e-07, + "loss": 0.0, + "num_tokens": 45836842.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 447 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 805.0, + "completions/mean_length": 1016.484375, + "completions/mean_terminated_length": 783.5, + "completions/min_length": 762.0, + "completions/min_terminated_length": 762.0, + "epoch": 0.2005820461159615, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.312957962878278e-07, + "loss": 0.0, + "num_tokens": 45936309.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 448 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20102977389747034, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.264344785909181e-07, + "loss": 0.0, + "num_tokens": 46039937.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 449 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 877.0, + "completions/mean_length": 1021.703125, + "completions/mean_terminated_length": 877.0, + "completions/min_length": 877.0, + "completions/min_terminated_length": 877.0, + "epoch": 0.20147750167897918, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.216622614502149e-07, + "loss": 0.0, + "num_tokens": 46147386.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 450 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20192522946048802, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.169793450983916e-07, + "loss": 0.0, + "num_tokens": 46242934.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 451 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 957.0, + "completions/mean_length": 1012.578125, + "completions/mean_terminated_length": 841.25, + "completions/min_length": 761.0, + "completions/min_terminated_length": 761.0, + "epoch": 0.20237295724199686, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.123859260212393e-07, + "loss": 0.0, + "num_tokens": 46344107.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 452 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2028206850235057, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.07882196949423e-07, + "loss": 0.0, + "num_tokens": 46448747.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 453 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20326841280501456, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 6.034683468503948e-07, + "loss": 0.0, + "num_tokens": 46554159.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 454 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2037161405865234, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.991445609204641e-07, + "loss": 0.0, + "num_tokens": 46658675.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 455 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20416386836803224, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.949110205770292e-07, + "loss": 0.0, + "num_tokens": 46758643.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 456 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 916.0, + "completions/mean_length": 1003.21875, + "completions/mean_terminated_length": 758.0, + "completions/min_length": 626.0, + "completions/min_terminated_length": 626.0, + "epoch": 0.20461159614954108, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.90767903450964e-07, + "loss": 0.0, + "num_tokens": 46859981.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 457 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20505932393104992, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.867153833791652e-07, + "loss": 0.0, + "num_tokens": 46961473.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 458 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20550705171255876, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.827536303972587e-07, + "loss": 0.0, + "num_tokens": 47069341.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 459 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2059547794940676, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.78882810732465e-07, + "loss": 0.0, + "num_tokens": 47168449.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 460 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20640250727557646, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.75103086796625e-07, + "loss": 0.0, + "num_tokens": 47267273.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 461 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 900.0, + "completions/mean_length": 1002.921875, + "completions/mean_terminated_length": 754.2000122070312, + "completions/min_length": 570.0, + "completions/min_terminated_length": 570.0, + "epoch": 0.2068502350570853, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.714146171793846e-07, + "loss": 0.0, + "num_tokens": 47364484.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 462 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20729796283859414, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.678175566415422e-07, + "loss": 0.0, + "num_tokens": 47465120.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 463 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 958.0, + "completions/mean_length": 1016.765625, + "completions/mean_terminated_length": 869.6666870117188, + "completions/min_length": 771.0, + "completions/min_terminated_length": 771.0, + "epoch": 0.20774569062010298, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.643120561085528e-07, + "loss": 0.0, + "num_tokens": 47567089.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 464 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 879.0, + "completions/mean_length": 1013.796875, + "completions/mean_terminated_length": 860.75, + "completions/min_length": 818.0, + "completions/min_terminated_length": 818.0, + "epoch": 0.20819341840161182, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.608982626641991e-07, + "loss": 0.0, + "num_tokens": 47668184.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 465 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20864114618312066, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.575763195444166e-07, + "loss": 0.0, + "num_tokens": 47776116.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 466 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 938.0, + "completions/mean_length": 1019.859375, + "completions/mean_terminated_length": 891.5, + "completions/min_length": 845.0, + "completions/min_terminated_length": 845.0, + "epoch": 0.2090888739646295, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.543463661312847e-07, + "loss": 0.0, + "num_tokens": 47874795.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 467 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.20953660174613833, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.512085379471808e-07, + "loss": 0.0, + "num_tokens": 47983267.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 468 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2099843295276472, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.481629666490903e-07, + "loss": 0.0, + "num_tokens": 48086875.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 469 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21043205730915604, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.452097800230853e-07, + "loss": 0.0, + "num_tokens": 48193671.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 470 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21087978509066488, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.423491019789623e-07, + "loss": 0.0, + "num_tokens": 48294211.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 471 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": -0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 992.0, + "completions/mean_length": 971.6875, + "completions/mean_terminated_length": 745.0, + "completions/min_length": 474.0, + "completions/min_terminated_length": 474.0, + "epoch": 0.21132751287217372, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.395810525450425e-07, + "loss": 0.0, + "num_tokens": 48388415.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 472 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 607.0, + "completions/mean_length": 1017.484375, + "completions/mean_terminated_length": 607.0, + "completions/min_length": 607.0, + "completions/min_terminated_length": 607.0, + "epoch": 0.21177524065368256, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.369057478631359e-07, + "loss": 0.0, + "num_tokens": 48490070.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 473 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 482.0, + "completions/mean_length": 984.96875, + "completions/mean_terminated_length": 399.5, + "completions/min_length": 332.0, + "completions/min_terminated_length": 332.0, + "epoch": 0.2122229684351914, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.343233001836694e-07, + "loss": 0.0, + "num_tokens": 48587284.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 474 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1020.0, + "completions/mean_length": 1023.9375, + "completions/mean_terminated_length": 1020.0, + "completions/min_length": 1020.0, + "completions/min_terminated_length": 1020.0, + "epoch": 0.21267069621670023, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.318338178609754e-07, + "loss": 0.0, + "num_tokens": 48689696.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 475 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 1013.0, + "completions/mean_length": 1023.515625, + "completions/mean_terminated_length": 1008.5, + "completions/min_length": 1004.0, + "completions/min_terminated_length": 1004.0, + "epoch": 0.2131184239982091, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.294374053487459e-07, + "loss": 0.0, + "num_tokens": 48789601.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 476 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 846.0, + "completions/mean_length": 1000.734375, + "completions/mean_terminated_length": 726.2000122070312, + "completions/min_length": 573.0, + "completions/min_terminated_length": 573.0, + "epoch": 0.21356615177971794, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.271341631956511e-07, + "loss": 0.0, + "num_tokens": 48890292.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 477 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21401387956122678, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.249241880411181e-07, + "loss": 0.0, + "num_tokens": 48994144.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 478 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.75, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 953.0, + "completions/mean_length": 1020.71875, + "completions/mean_terminated_length": 919.0, + "completions/min_length": 885.0, + "completions/min_terminated_length": 885.0, + "epoch": 0.21446160734273562, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.228075726112785e-07, + "loss": 0.0, + "num_tokens": 49092138.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 479 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21490933512424445, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.207844057150768e-07, + "loss": 0.0, + "num_tokens": 49196678.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 480 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2153570629057533, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.188547722405437e-07, + "loss": 0.0, + "num_tokens": 49301646.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 481 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 833.0, + "completions/mean_length": 1006.015625, + "completions/mean_terminated_length": 640.3333740234375, + "completions/min_length": 435.0, + "completions/min_terminated_length": 435.0, + "epoch": 0.21580479068726213, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.170187531512351e-07, + "loss": 0.0, + "num_tokens": 49403619.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 482 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 909.0, + "completions/mean_length": 1003.28125, + "completions/mean_terminated_length": 692.5, + "completions/min_length": 589.0, + "completions/min_terminated_length": 589.0, + "epoch": 0.216252518468771, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.152764254828348e-07, + "loss": 0.0, + "num_tokens": 49502757.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 483 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21670024625027984, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.136278623399225e-07, + "loss": 0.0, + "num_tokens": 49609485.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 484 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 949.0, + "completions/mean_length": 1013.921875, + "completions/mean_terminated_length": 809.0, + "completions/min_length": 608.0, + "completions/min_terminated_length": 608.0, + "epoch": 0.21714797403178868, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.120731328929058e-07, + "loss": 0.0, + "num_tokens": 49710368.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 485 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 947.0, + "completions/mean_length": 1007.3125, + "completions/mean_terminated_length": 810.4000244140625, + "completions/min_length": 681.0, + "completions/min_terminated_length": 681.0, + "epoch": 0.21759570181329752, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.106123023751187e-07, + "loss": 0.0, + "num_tokens": 49814492.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 486 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21804342959480635, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.092454320800833e-07, + "loss": 0.0, + "num_tokens": 49915068.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 487 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 861.0, + "completions/mean_length": 1005.4375, + "completions/mean_terminated_length": 727.0, + "completions/min_length": 476.0, + "completions/min_terminated_length": 476.0, + "epoch": 0.2184911573763152, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.079725793589405e-07, + "loss": 0.0, + "num_tokens": 50028228.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 488 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.21893888515782403, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.067937976180407e-07, + "loss": 0.0, + "num_tokens": 50137732.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 489 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 968.0, + "completions/mean_length": 1017.6875, + "completions/mean_terminated_length": 889.3333740234375, + "completions/min_length": 843.0, + "completions/min_terminated_length": 843.0, + "epoch": 0.2193866129393329, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.057091363167046e-07, + "loss": 0.0, + "num_tokens": 50243552.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 490 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.625, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 887.0, + "completions/mean_length": 1012.0, + "completions/mean_terminated_length": 768.0, + "completions/min_length": 638.0, + "completions/min_terminated_length": 638.0, + "epoch": 0.21983434072084174, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.047186409651489e-07, + "loss": 0.0, + "num_tokens": 50345332.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 491 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.22028206850235058, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.038223531225742e-07, + "loss": 0.0, + "num_tokens": 50446008.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 492 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.22072979628385941, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.030203103954232e-07, + "loss": 0.0, + "num_tokens": 50542328.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 493 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.22117752406536825, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.023125464358026e-07, + "loss": 0.0, + "num_tokens": 50649272.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 494 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2216252518468771, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.016990909400709e-07, + "loss": 0.0, + "num_tokens": 50756244.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 495 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.375, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 931.0, + "completions/mean_length": 1002.515625, + "completions/mean_terminated_length": 749.0, + "completions/min_length": 597.0, + "completions/min_terminated_length": 597.0, + "epoch": 0.22207297962838593, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.011799696475915e-07, + "loss": 0.0, + "num_tokens": 50855153.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 496 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 971.0, + "completions/mean_length": 1023.171875, + "completions/mean_terminated_length": 971.0, + "completions/min_length": 971.0, + "completions/min_terminated_length": 971.0, + "epoch": 0.2225207074098948, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.007552043396547e-07, + "loss": 0.0, + "num_tokens": 50956480.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 497 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.875, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 975.0, + "completions/mean_length": 1023.234375, + "completions/mean_terminated_length": 975.0, + "completions/min_length": 975.0, + "completions/min_terminated_length": 975.0, + "epoch": 0.22296843519140364, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.004248128385618e-07, + "loss": 0.0, + "num_tokens": 51056271.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 498 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.5, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 915.0, + "completions/mean_length": 1015.015625, + "completions/mean_terminated_length": 880.25, + "completions/min_length": 800.0, + "completions/min_terminated_length": 800.0, + "epoch": 0.22341616297291247, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.001888090068784e-07, + "loss": 0.0, + "num_tokens": 51156260.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 499 + }, + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 1.0, + "completions/max_length": 1024.0, + "completions/max_terminated_length": 0.0, + "completions/mean_length": 1024.0, + "completions/mean_terminated_length": 0.0, + "completions/min_length": 1024.0, + "completions/min_terminated_length": 0.0, + "epoch": 0.2238638907544213, + "frac_reward_zero_std": 1.0, + "grad_norm": 0.0, + "kl": 0.0, + "learning_rate": 5.000472027468528e-07, + "loss": 0.0, + "num_tokens": 51260808.0, + "reward": 0.0, + "reward_std": 0.0, + "rewards/code_reward/mean": 0.0, + "rewards/code_reward/std": 0.0, + "rewards/format_reward/mean": 0.0, + "rewards/format_reward/std": 0.0, + "step": 500 + }, + { + "epoch": 0.2238638907544213, + "step": 500, + "total_flos": 0.0, + "train_loss": 0.0, + "train_runtime": 19152.9917, + "train_samples_per_second": 1.671, + "train_steps_per_second": 0.026 + } + ], + "logging_steps": 1, + "max_steps": 500, + "num_input_tokens_seen": 51260808, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +}