{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 4124, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.24248302618816683, "grad_norm": 22.99319839477539, "learning_rate": 2.929668552950687e-05, "loss": 1.9432, "step": 500 }, { "epoch": 0.48496605237633367, "grad_norm": 29.776500701904297, "learning_rate": 2.5254648342764755e-05, "loss": 1.0335, "step": 1000 }, { "epoch": 0.7274490785645005, "grad_norm": 17.826507568359375, "learning_rate": 2.1212611156022636e-05, "loss": 0.9314, "step": 1500 }, { "epoch": 0.9699321047526673, "grad_norm": 16.028316497802734, "learning_rate": 1.7170573969280517e-05, "loss": 0.875, "step": 2000 }, { "epoch": 1.2124151309408342, "grad_norm": 27.188560485839844, "learning_rate": 1.31285367825384e-05, "loss": 0.7128, "step": 2500 }, { "epoch": 1.454898157129001, "grad_norm": 15.629920959472656, "learning_rate": 9.086499595796281e-06, "loss": 0.6671, "step": 3000 }, { "epoch": 1.6973811833171677, "grad_norm": 15.22022819519043, "learning_rate": 5.044462409054164e-06, "loss": 0.6666, "step": 3500 }, { "epoch": 1.9398642095053347, "grad_norm": 21.28203582763672, "learning_rate": 1.0024252223120454e-06, "loss": 0.641, "step": 4000 } ], "logging_steps": 500, "max_steps": 4124, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4371201741330432.0, "train_batch_size": 64, "trial_name": null, "trial_params": null }