{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.3988035892323031, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03988035892323031, "grad_norm": 13.419048309326172, "learning_rate": 0.0002, "loss": 3.2212, "step": 10 }, { "epoch": 0.07976071784646062, "grad_norm": 3.605897903442383, "learning_rate": 0.00019863613034027224, "loss": 0.9339, "step": 20 }, { "epoch": 0.11964107676969092, "grad_norm": 1.9724041223526, "learning_rate": 0.00019458172417006347, "loss": 0.4623, "step": 30 }, { "epoch": 0.15952143569292124, "grad_norm": 1.7109146118164062, "learning_rate": 0.0001879473751206489, "loss": 0.3536, "step": 40 }, { "epoch": 0.19940179461615154, "grad_norm": 0.9077266454696655, "learning_rate": 0.00017891405093963938, "loss": 0.3476, "step": 50 }, { "epoch": 0.23928215353938184, "grad_norm": 1.310617446899414, "learning_rate": 0.00016772815716257412, "loss": 0.3369, "step": 60 }, { "epoch": 0.27916251246261214, "grad_norm": 0.8259612321853638, "learning_rate": 0.00015469481581224272, "loss": 0.3062, "step": 70 }, { "epoch": 0.3190428713858425, "grad_norm": 1.113377571105957, "learning_rate": 0.00014016954246529696, "loss": 0.2959, "step": 80 }, { "epoch": 0.3589232303090728, "grad_norm": 1.0124801397323608, "learning_rate": 0.00012454854871407994, "loss": 0.3015, "step": 90 }, { "epoch": 0.3988035892323031, "grad_norm": 2.501101016998291, "learning_rate": 0.00010825793454723325, "loss": 0.31, "step": 100 } ], "logging_steps": 10, "max_steps": 200, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 363212598927360.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }