{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4e-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": 573.0, "completions/max_terminated_length": 573.0, "completions/mean_length": 125.71875, "completions/mean_terminated_length": 125.71875, "completions/min_length": 2.0, "completions/min_terminated_length": 2.0, "entropy": 1.372788105159998, "epoch": 4e-05, "frac_reward_zero_std": 0.0, "grad_norm": 0.7595316171646118, "kl": 0.0, "learning_rate": 0.0, "loss": -0.0345, "num_tokens": 91750.0, "reward": -0.6493574976921082, "reward_std": 0.7037926316261292, "rewards/rollout_reward_func/mean": -0.6493574976921082, "rewards/rollout_reward_func/std": 0.8106608986854553, "sampling/importance_sampling_ratio/max": 1.3807494640350342, "sampling/importance_sampling_ratio/mean": 1.0163333415985107, "sampling/importance_sampling_ratio/min": 0.7142292261123657, "sampling/sampling_logp_difference/max": 0.23920273780822754, "sampling/sampling_logp_difference/mean": 0.028075017035007477, "step": 1, "step_time": 10.923513879000893 } ], "logging_steps": 1.0, "max_steps": 1800, "num_input_tokens_seen": 91750, "num_train_epochs": 1, "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 }