| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "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": 0.0, | |
| "completions/max_length": 26.0, | |
| "completions/max_terminated_length": 26.0, | |
| "completions/mean_length": 24.0, | |
| "completions/mean_terminated_length": 24.0, | |
| "completions/min_length": 22.0, | |
| "completions/min_terminated_length": 22.0, | |
| "epoch": 2.0, | |
| "frac_reward_zero_std": 1.0, | |
| "grad_norm": 0.0, | |
| "kl": 0.0, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0, | |
| "num_tokens": 1216.0, | |
| "reward": 2.4478299617767334, | |
| "reward_std": 0.0, | |
| "rewards/concensus_correctness_reward_func/mean": 0.0, | |
| "rewards/concensus_correctness_reward_func/std": 0.0, | |
| "rewards/consensus_reward_func/mean": 0.0, | |
| "rewards/consensus_reward_func/std": 0.0, | |
| "rewards/cumulative_reward_2/mean": 0.0, | |
| "rewards/cumulative_reward_2/std": 0.0, | |
| "rewards/final_correctness_reward_func/mean": 2.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.009830009657889605, | |
| "rewards/question_recreation_reward_func/std": 0.005444320850074291, | |
| "rewards/soft_format_reward_func/mean": 0.0, | |
| "rewards/soft_format_reward_func/std": 0.0, | |
| "rewards/strict_format_reward_func/mean": 0.0, | |
| "rewards/strict_format_reward_func/std": 0.0, | |
| "rewards/xmlcount_reward_func/mean": 0.43800000846385956, | |
| "rewards/xmlcount_reward_func/std": 0.0023094057105481625, | |
| "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": 0.0, | |
| "completions/max_length": 26.0, | |
| "completions/max_terminated_length": 26.0, | |
| "completions/mean_length": 24.0, | |
| "completions/mean_terminated_length": 24.0, | |
| "completions/min_length": 22.0, | |
| "completions/min_terminated_length": 22.0, | |
| "epoch": 4.0, | |
| "frac_reward_zero_std": 1.0, | |
| "grad_norm": 0.0, | |
| "kl": 0.0, | |
| "learning_rate": 4.415111107797445e-07, | |
| "loss": 0.0, | |
| "num_tokens": 2432.0, | |
| "reward": 2.4532930850982666, | |
| "reward_std": 0.0, | |
| "rewards/concensus_correctness_reward_func/mean": 0.0, | |
| "rewards/concensus_correctness_reward_func/std": 0.0, | |
| "rewards/consensus_reward_func/mean": 0.0, | |
| "rewards/consensus_reward_func/std": 0.0, | |
| "rewards/cumulative_reward_2/mean": 0.0, | |
| "rewards/cumulative_reward_2/std": 0.0, | |
| "rewards/final_correctness_reward_func/mean": 2.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.01529320701956749, | |
| "rewards/question_recreation_reward_func/std": 0.005846281070262194, | |
| "rewards/soft_format_reward_func/mean": 0.0, | |
| "rewards/soft_format_reward_func/std": 0.0, | |
| "rewards/strict_format_reward_func/mean": 0.0, | |
| "rewards/strict_format_reward_func/std": 0.0, | |
| "rewards/xmlcount_reward_func/mean": 0.43800002336502075, | |
| "rewards/xmlcount_reward_func/std": 0.0023094057105481625, | |
| "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": 0.0, | |
| "completions/max_length": 26.0, | |
| "completions/max_terminated_length": 26.0, | |
| "completions/mean_length": 24.0, | |
| "completions/mean_terminated_length": 24.0, | |
| "completions/min_length": 22.0, | |
| "completions/min_terminated_length": 22.0, | |
| "epoch": 6.0, | |
| "frac_reward_zero_std": 1.0, | |
| "grad_norm": 0.0, | |
| "kl": 0.0, | |
| "learning_rate": 2.934120444167326e-07, | |
| "loss": 0.0, | |
| "num_tokens": 3648.0, | |
| "reward": 2.4478299617767334, | |
| "reward_std": 0.0, | |
| "rewards/concensus_correctness_reward_func/mean": 0.0, | |
| "rewards/concensus_correctness_reward_func/std": 0.0, | |
| "rewards/consensus_reward_func/mean": 0.0, | |
| "rewards/consensus_reward_func/std": 0.0, | |
| "rewards/cumulative_reward_2/mean": 0.0, | |
| "rewards/cumulative_reward_2/std": 0.0, | |
| "rewards/final_correctness_reward_func/mean": 2.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.009830009657889605, | |
| "rewards/question_recreation_reward_func/std": 0.005444320850074291, | |
| "rewards/soft_format_reward_func/mean": 0.0, | |
| "rewards/soft_format_reward_func/std": 0.0, | |
| "rewards/strict_format_reward_func/mean": 0.0, | |
| "rewards/strict_format_reward_func/std": 0.0, | |
| "rewards/xmlcount_reward_func/mean": 0.43800000846385956, | |
| "rewards/xmlcount_reward_func/std": 0.0023094057105481625, | |
| "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": 0.0, | |
| "completions/max_length": 26.0, | |
| "completions/max_terminated_length": 26.0, | |
| "completions/mean_length": 24.0, | |
| "completions/mean_terminated_length": 24.0, | |
| "completions/min_length": 22.0, | |
| "completions/min_terminated_length": 22.0, | |
| "epoch": 8.0, | |
| "frac_reward_zero_std": 1.0, | |
| "grad_norm": 0.0, | |
| "kl": 0.0, | |
| "learning_rate": 1.2500000000000005e-07, | |
| "loss": 0.0, | |
| "num_tokens": 4864.0, | |
| "reward": 2.4532930850982666, | |
| "reward_std": 0.0, | |
| "rewards/concensus_correctness_reward_func/mean": 0.0, | |
| "rewards/concensus_correctness_reward_func/std": 0.0, | |
| "rewards/consensus_reward_func/mean": 0.0, | |
| "rewards/consensus_reward_func/std": 0.0, | |
| "rewards/cumulative_reward_2/mean": 0.0, | |
| "rewards/cumulative_reward_2/std": 0.0, | |
| "rewards/final_correctness_reward_func/mean": 2.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.01529320701956749, | |
| "rewards/question_recreation_reward_func/std": 0.005846281070262194, | |
| "rewards/soft_format_reward_func/mean": 0.0, | |
| "rewards/soft_format_reward_func/std": 0.0, | |
| "rewards/strict_format_reward_func/mean": 0.0, | |
| "rewards/strict_format_reward_func/std": 0.0, | |
| "rewards/xmlcount_reward_func/mean": 0.43800002336502075, | |
| "rewards/xmlcount_reward_func/std": 0.0023094057105481625, | |
| "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": 0.0, | |
| "completions/max_length": 26.0, | |
| "completions/max_terminated_length": 26.0, | |
| "completions/mean_length": 24.0, | |
| "completions/mean_terminated_length": 24.0, | |
| "completions/min_length": 22.0, | |
| "completions/min_terminated_length": 22.0, | |
| "epoch": 10.0, | |
| "frac_reward_zero_std": 1.0, | |
| "grad_norm": 0.0, | |
| "kl": 0.0, | |
| "learning_rate": 1.507684480352292e-08, | |
| "loss": 0.0, | |
| "num_tokens": 6080.0, | |
| "reward": 2.4478299617767334, | |
| "reward_std": 0.0, | |
| "rewards/concensus_correctness_reward_func/mean": 0.0, | |
| "rewards/concensus_correctness_reward_func/std": 0.0, | |
| "rewards/consensus_reward_func/mean": 0.0, | |
| "rewards/consensus_reward_func/std": 0.0, | |
| "rewards/cumulative_reward_2/mean": 0.0, | |
| "rewards/cumulative_reward_2/std": 0.0, | |
| "rewards/final_correctness_reward_func/mean": 2.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.009830009657889605, | |
| "rewards/question_recreation_reward_func/std": 0.005444320850074291, | |
| "rewards/soft_format_reward_func/mean": 0.0, | |
| "rewards/soft_format_reward_func/std": 0.0, | |
| "rewards/strict_format_reward_func/mean": 0.0, | |
| "rewards/strict_format_reward_func/std": 0.0, | |
| "rewards/xmlcount_reward_func/mean": 0.43800000846385956, | |
| "rewards/xmlcount_reward_func/std": 0.0023094057105481625, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 10, | |
| "total_flos": 0.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 277.6317, | |
| "train_samples_per_second": 0.144, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 6080, | |
| "num_train_epochs": 10, | |
| "save_steps": 10, | |
| "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 | |
| } | |