{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 78, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.38461538461538464, "grad_norm": 0.7253261543104126, "learning_rate": 9.979871469976197e-06, "loss": 0.4062, "step": 10 }, { "epoch": 0.7692307692307693, "grad_norm": 0.4193514959958101, "learning_rate": 9.292243968009332e-06, "loss": 0.3954, "step": 20 }, { "epoch": 1.1538461538461537, "grad_norm": 0.43732575229679993, "learning_rate": 7.754484907260513e-06, "loss": 0.3389, "step": 30 }, { "epoch": 1.5384615384615383, "grad_norm": 0.43733481719480727, "learning_rate": 5.671166329088278e-06, "loss": 0.3296, "step": 40 }, { "epoch": 1.9230769230769231, "grad_norm": 0.3990439199728364, "learning_rate": 3.4549150281252635e-06, "loss": 0.3183, "step": 50 }, { "epoch": 2.3076923076923075, "grad_norm": 0.31428396418963495, "learning_rate": 1.544686755065677e-06, "loss": 0.2884, "step": 60 }, { "epoch": 2.6923076923076925, "grad_norm": 0.2953019492946096, "learning_rate": 3.18825646801314e-07, "loss": 0.2566, "step": 70 }, { "epoch": 3.0, "step": 78, "total_flos": 17907093995520.0, "train_loss": 0.32062222101749516, "train_runtime": 876.6394, "train_samples_per_second": 1.41, "train_steps_per_second": 0.089 } ], "logging_steps": 10, "max_steps": 78, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 17907093995520.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }