{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.128, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0128, "grad_norm": 3.444922924041748, "learning_rate": 9.900000000000001e-05, "loss": 8.219487915039062, "step": 100 }, { "epoch": 0.0256, "grad_norm": 0.8677482008934021, "learning_rate": 0.000199, "loss": 2.852702331542969, "step": 200 }, { "epoch": 0.0384, "grad_norm": 1.1583627462387085, "learning_rate": 0.000299, "loss": 1.72166259765625, "step": 300 }, { "epoch": 0.0512, "grad_norm": 1.3285731077194214, "learning_rate": 0.00039900000000000005, "loss": 1.4859967041015625, "step": 400 }, { "epoch": 0.064, "grad_norm": 0.5119664669036865, "learning_rate": 0.000499, "loss": 1.3544009399414063, "step": 500 }, { "epoch": 0.0768, "grad_norm": 0.5693696737289429, "learning_rate": 0.0004999682018599242, "loss": 1.2615775299072265, "step": 600 }, { "epoch": 0.0896, "grad_norm": 0.38031378388404846, "learning_rate": 0.0004998715277031906, "loss": 1.1965968322753906, "step": 700 }, { "epoch": 0.1024, "grad_norm": 0.4511842131614685, "learning_rate": 0.0004997099993771365, "loss": 1.137486572265625, "step": 800 }, { "epoch": 0.1152, "grad_norm": 0.3763165771961212, "learning_rate": 0.000499483658806448, "loss": 1.0960751342773438, "step": 900 }, { "epoch": 0.128, "grad_norm": 0.39710113406181335, "learning_rate": 0.0004991925647378331, "loss": 1.0592382049560547, "step": 1000 } ], "logging_steps": 100, "max_steps": 20000, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4186636812288000.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }