| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4878048780487805, | |
| "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": 127.0, | |
| "completions/max_terminated_length": 127.0, | |
| "completions/mean_length": 59.25, | |
| "completions/mean_terminated_length": 59.25, | |
| "completions/min_length": 13.0, | |
| "completions/min_terminated_length": 13.0, | |
| "epoch": 0.0975609756097561, | |
| "frac_reward_zero_std": 0.0, | |
| "grad_norm": 25.766353607177734, | |
| "kl": 0.0, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0186, | |
| "num_tokens": 1498.0, | |
| "reward": 0.049393012188374996, | |
| "reward_std": 0.048807840794324875, | |
| "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": 0.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.02114301174879074, | |
| "rewards/question_recreation_reward_func/std": 0.0122159318998456, | |
| "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": 0.02824999950826168, | |
| "rewards/xmlcount_reward_func/std": 0.05649999901652336, | |
| "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": 132.0, | |
| "completions/max_terminated_length": 132.0, | |
| "completions/mean_length": 53.75, | |
| "completions/mean_terminated_length": 53.75, | |
| "completions/min_length": 24.5, | |
| "completions/min_terminated_length": 24.5, | |
| "epoch": 0.1951219512195122, | |
| "frac_reward_zero_std": 0.25, | |
| "grad_norm": 19.915145874023438, | |
| "kl": 0.0023184213787317276, | |
| "learning_rate": 4.415111107797445e-07, | |
| "loss": 0.0505, | |
| "num_tokens": 2952.0, | |
| "reward": 0.04935022257268429, | |
| "reward_std": 0.05023687332868576, | |
| "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": 0.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.018100222572684288, | |
| "rewards/question_recreation_reward_func/std": 0.012556762900203466, | |
| "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": 0.03125, | |
| "rewards/xmlcount_reward_func/std": 0.0625, | |
| "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": 67.5, | |
| "completions/max_terminated_length": 67.5, | |
| "completions/mean_length": 28.25, | |
| "completions/mean_terminated_length": 28.25, | |
| "completions/min_length": 5.5, | |
| "completions/min_terminated_length": 5.5, | |
| "epoch": 0.2926829268292683, | |
| "frac_reward_zero_std": 0.0, | |
| "grad_norm": 97.34249877929688, | |
| "kl": 0.01801438198890537, | |
| "learning_rate": 2.934120444167326e-07, | |
| "loss": -0.16, | |
| "num_tokens": 4202.0, | |
| "reward": 0.114079300314188, | |
| "reward_std": 0.08150303550064564, | |
| "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": 0.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.08282929984852672, | |
| "rewards/question_recreation_reward_func/std": 0.03306010598316789, | |
| "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": 0.03125, | |
| "rewards/xmlcount_reward_func/std": 0.0625, | |
| "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": 75.5, | |
| "completions/max_terminated_length": 75.5, | |
| "completions/mean_length": 36.875, | |
| "completions/mean_terminated_length": 36.875, | |
| "completions/min_length": 16.0, | |
| "completions/min_terminated_length": 16.0, | |
| "epoch": 0.3902439024390244, | |
| "frac_reward_zero_std": 0.25, | |
| "grad_norm": 50.915489196777344, | |
| "kl": 0.019150954321958125, | |
| "learning_rate": 1.2500000000000005e-07, | |
| "loss": -0.0363, | |
| "num_tokens": 5521.0, | |
| "reward": 0.13781297951936722, | |
| "reward_std": 0.03136043483391404, | |
| "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": 0.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.028437979985028505, | |
| "rewards/question_recreation_reward_func/std": 0.010751228081062436, | |
| "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": 0.109375, | |
| "rewards/xmlcount_reward_func/std": 0.13200797885656357, | |
| "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": 120.5, | |
| "completions/max_terminated_length": 120.5, | |
| "completions/mean_length": 44.25, | |
| "completions/mean_terminated_length": 44.25, | |
| "completions/min_length": 12.5, | |
| "completions/min_terminated_length": 12.5, | |
| "epoch": 0.4878048780487805, | |
| "frac_reward_zero_std": 0.25, | |
| "grad_norm": 31.54133415222168, | |
| "kl": 0.02116560866124928, | |
| "learning_rate": 1.507684480352292e-08, | |
| "loss": 0.0382, | |
| "num_tokens": 6899.0, | |
| "reward": 0.08553153276443481, | |
| "reward_std": 0.019916290184482932, | |
| "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": 0.0, | |
| "rewards/final_correctness_reward_func/std": 0.0, | |
| "rewards/question_recreation_reward_func/mean": 0.013406533282250166, | |
| "rewards/question_recreation_reward_func/std": 0.013068773550912738, | |
| "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": 0.07212499901652336, | |
| "rewards/xmlcount_reward_func/std": 0.09649057686328888, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "step": 10, | |
| "total_flos": 0.0, | |
| "train_loss": -0.01780639439821243, | |
| "train_runtime": 1859.9628, | |
| "train_samples_per_second": 0.022, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 6899, | |
| "num_train_epochs": 1, | |
| "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 | |
| } | |