| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2e-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": 0.0, |
| "completions/max_length": 850.0, |
| "completions/max_terminated_length": 850.0, |
| "completions/mean_length": 209.34375, |
| "completions/mean_terminated_length": 209.34375, |
| "completions/min_length": 2.0, |
| "completions/min_terminated_length": 2.0, |
| "entropy": 0.5074248900637031, |
| "epoch": 2e-05, |
| "frac_reward_zero_std": 0.0, |
| "grad_norm": 2.6727540493011475, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": 0.0288, |
| "num_tokens": 53144.0, |
| "reward": -0.4268425405025482, |
| "reward_std": 1.716860294342041, |
| "rewards/rollout_reward_func/mean": -0.4268425405025482, |
| "rewards/rollout_reward_func/std": 1.7247568368911743, |
| "sampling/importance_sampling_ratio/max": 1.791617751121521, |
| "sampling/importance_sampling_ratio/mean": 1.0094280242919922, |
| "sampling/importance_sampling_ratio/min": 0.0, |
| "sampling/sampling_logp_difference/max": 1.517822265625, |
| "sampling/sampling_logp_difference/mean": 0.058271829038858414, |
| "step": 1, |
| "step_time": 89.26485159500317 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 100000, |
| "num_input_tokens_seen": 53144, |
| "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": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
