{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1e-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": 0.03125, "completions/max_length": 942.0, "completions/max_terminated_length": 942.0, "completions/mean_length": 390.375, "completions/mean_terminated_length": 389.32257080078125, "completions/min_length": 2.0, "completions/min_terminated_length": 2.0, "entropy": 8.502744436264038, "epoch": 1e-05, "frac_reward_zero_std": 0.0, "grad_norm": 0.007989775389432907, "kl": 0.0, "learning_rate": 0.0, "loss": 0.0002, "num_tokens": 49300.0, "reward": 0.5077679753303528, "reward_std": 1.4316442012786865, "rewards/rollout_reward_func/mean": 0.5077679753303528, "rewards/rollout_reward_func/std": 1.383098840713501, "sampling/importance_sampling_ratio/max": 0.05534586310386658, "sampling/importance_sampling_ratio/mean": 0.0062338062562048435, "sampling/importance_sampling_ratio/min": 6.590540592920583e-15, "sampling/sampling_logp_difference/max": 4.380148410797119, "sampling/sampling_logp_difference/mean": 1.538283348083496, "step": 1, "step_time": 9.570080434999909 } ], "logging_steps": 1.0, "max_steps": 200000, "num_input_tokens_seen": 49300, "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 }