| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3072, |
| "eval_steps": 50, |
| "global_step": 12, |
| "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": 0.0013671875, |
| "completions/max_length": 1536.0, |
| "completions/max_terminated_length": 743.8, |
| "completions/mean_length": 43.950927734375, |
| "completions/mean_terminated_length": 41.91697196960449, |
| "completions/min_length": 2.0, |
| "completions/min_terminated_length": 2.0, |
| "epoch": 0.128, |
| "grad_norm": 0.031575221568346024, |
| "learning_rate": 1e-06, |
| "loss": -0.0301, |
| "num_tokens": 24591611.0, |
| "reward": 0.283935546875, |
| "reward_std": 0.19546712040901185, |
| "rewards/accuracy_reward": 0.099853515625, |
| "rewards/brier_reward": 0.0, |
| "rewards/confidence_one_or_zero": 0.0, |
| "rewards/format_reward": 0.468017578125, |
| "rewards/mean_confidence_reward": 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": 0.00185546875, |
| "completions/max_length": 1536.0, |
| "completions/max_terminated_length": 1001.8, |
| "completions/mean_length": 74.304150390625, |
| "completions/mean_terminated_length": 71.58470611572265, |
| "completions/min_length": 3.0, |
| "completions/min_terminated_length": 3.0, |
| "epoch": 0.256, |
| "grad_norm": 0.005221568513661623, |
| "learning_rate": 1e-06, |
| "loss": 0.0247, |
| "num_tokens": 49954800.0, |
| "reward": 0.5662353515625, |
| "reward_std": 0.17715120315551758, |
| "rewards/accuracy_reward": 0.214404296875, |
| "rewards/brier_reward": 0.0, |
| "rewards/confidence_one_or_zero": 0.0, |
| "rewards/format_reward": 0.91806640625, |
| "rewards/mean_confidence_reward": 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": 0.00244140625, |
| "completions/max_length": 1536.0, |
| "completions/max_terminated_length": 1212.0, |
| "completions/mean_length": 83.727294921875, |
| "completions/mean_terminated_length": 80.17552947998047, |
| "completions/min_length": 7.5, |
| "completions/min_terminated_length": 7.5, |
| "epoch": 0.3072, |
| "num_tokens": 60102742.0, |
| "reward": 0.6011962890625, |
| "reward_std": 0.13282935321331024, |
| "rewards/accuracy_reward": 0.2298583984375, |
| "rewards/brier_reward": 0.0, |
| "rewards/confidence_one_or_zero": 0.0, |
| "rewards/format_reward": 0.9725341796875, |
| "rewards/mean_confidence_reward": 0.0, |
| "step": 12, |
| "total_flos": 0.0, |
| "train_loss": 0.0016811620444059372, |
| "train_runtime": 1935.2642, |
| "train_samples_per_second": 3.1, |
| "train_steps_per_second": 0.006 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 12, |
| "num_input_tokens_seen": 60102742, |
| "num_train_epochs": 1, |
| "save_steps": 60, |
| "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": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
