{ "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": 812.0, "completions/max_terminated_length": 812.0, "completions/mean_length": 735.03125, "completions/mean_terminated_length": 735.03125, "completions/min_length": 289.0, "completions/min_terminated_length": 289.0, "entropy": 0.5412971004843712, "epoch": 2e-05, "frac_reward_zero_std": 0.0, "grad_norm": 1.1536695957183838, "kl": 0.0, "learning_rate": 0.0, "loss": 0.0246, "num_tokens": 50452.0, "reward": -0.8646370768547058, "reward_std": 10.58029842376709, "rewards/rollout_reward_func/mean": -0.8646370768547058, "rewards/rollout_reward_func/std": 10.609013557434082, "sampling/importance_sampling_ratio/max": 1.2036820650100708, "sampling/importance_sampling_ratio/mean": 0.965369701385498, "sampling/importance_sampling_ratio/min": 0.5870557427406311, "sampling/sampling_logp_difference/max": 0.24155187606811523, "sampling/sampling_logp_difference/mean": 0.02399737387895584, "step": 1, "step_time": 11.547345764000056 } ], "logging_steps": 1.0, "max_steps": 100000, "num_input_tokens_seen": 50452, "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 }