| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 8e-05, |
| "eval_steps": 500, |
| "global_step": 1, |
| "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": 0.15625, |
| "completions/max_length": 16.0, |
| "completions/max_terminated_length": 15.0, |
| "completions/mean_length": 7.53125, |
| "completions/mean_terminated_length": 5.962963104248047, |
| "completions/min_length": 3.0, |
| "completions/min_terminated_length": 3.0, |
| "entropy": 0.837708592414856, |
| "epoch": 8e-05, |
| "frac_reward_zero_std": 0.25, |
| "grad_norm": 0.693935215473175, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": 0.0929, |
| "num_tokens": 20981.0, |
| "reward": -0.06562499701976776, |
| "reward_std": 0.04825586825609207, |
| "rewards/rollout_reward_func/mean": -0.06562499701976776, |
| "rewards/rollout_reward_func/std": 0.04825586825609207, |
| "sampling/importance_sampling_ratio/max": 1.1812933683395386, |
| "sampling/importance_sampling_ratio/mean": 0.9682762622833252, |
| "sampling/importance_sampling_ratio/min": 0.7112594842910767, |
| "sampling/sampling_logp_difference/max": 0.22895026206970215, |
| "sampling/sampling_logp_difference/mean": 0.02356213517487049, |
| "step": 1, |
| "step_time": 5.666027546998521 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 25000, |
| "num_input_tokens_seen": 20981, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "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 |
| } |
|
|
