{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.882352941176471, "eval_steps": 500, "global_step": 300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5882352941176471, "grad_norm": 0.39919430017471313, "learning_rate": 2.5e-05, "loss": 1.4153, "step": 30 }, { "epoch": 1.1764705882352942, "grad_norm": 0.6906107664108276, "learning_rate": 5e-05, "loss": 1.3019, "step": 60 }, { "epoch": 1.7647058823529411, "grad_norm": 0.7136546969413757, "learning_rate": 4.8096988312782174e-05, "loss": 1.0532, "step": 90 }, { "epoch": 2.3529411764705883, "grad_norm": 0.979485034942627, "learning_rate": 4.267766952966369e-05, "loss": 0.7964, "step": 120 }, { "epoch": 2.9411764705882355, "grad_norm": 1.1987406015396118, "learning_rate": 3.456708580912725e-05, "loss": 0.5561, "step": 150 }, { "epoch": 3.5294117647058822, "grad_norm": 1.4430248737335205, "learning_rate": 2.5e-05, "loss": 0.3678, "step": 180 }, { "epoch": 4.117647058823529, "grad_norm": 1.415720820426941, "learning_rate": 1.5432914190872757e-05, "loss": 0.3576, "step": 210 }, { "epoch": 4.705882352941177, "grad_norm": 0.9879446625709534, "learning_rate": 7.3223304703363135e-06, "loss": 0.3174, "step": 240 }, { "epoch": 5.294117647058823, "grad_norm": 1.1644922494888306, "learning_rate": 1.9030116872178316e-06, "loss": 0.2657, "step": 270 }, { "epoch": 5.882352941176471, "grad_norm": 1.1767199039459229, "learning_rate": 0.0, "loss": 0.2573, "step": 300 } ], "logging_steps": 30, "max_steps": 300, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.1298211097321472e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }