{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.06153609476558594, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006153609476558594, "grad_norm": 25468.8046875, "learning_rate": 1.9999999999999996e-07, "loss": 8.7082, "step": 10 }, { "epoch": 0.012307218953117188, "grad_norm": 1228.4501953125, "learning_rate": 1.2e-06, "loss": 8.0776, "step": 20 }, { "epoch": 0.018460828429675783, "grad_norm": 355.1081237792969, "learning_rate": 2.1999999999999997e-06, "loss": 7.2372, "step": 30 }, { "epoch": 0.024614437906234375, "grad_norm": 255.58433532714844, "learning_rate": 3.1999999999999994e-06, "loss": 6.9725, "step": 40 }, { "epoch": 0.03076804738279297, "grad_norm": 253.23995971679688, "learning_rate": 4.2e-06, "loss": 6.8585, "step": 50 }, { "epoch": 0.036921656859351566, "grad_norm": 241.82064819335938, "learning_rate": 5.199999999999999e-06, "loss": 6.7367, "step": 60 }, { "epoch": 0.043075266335910155, "grad_norm": 229.0261993408203, "learning_rate": 6.199999999999999e-06, "loss": 6.6534, "step": 70 }, { "epoch": 0.04922887581246875, "grad_norm": 321.6871337890625, "learning_rate": 7.2e-06, "loss": 6.6305, "step": 80 }, { "epoch": 0.055382485289027346, "grad_norm": 465.00543212890625, "learning_rate": 8.2e-06, "loss": 6.6253, "step": 90 }, { "epoch": 0.06153609476558594, "grad_norm": 566.6929321289062, "learning_rate": 9.199999999999998e-06, "loss": 6.5724, "step": 100 } ], "logging_steps": 10, "max_steps": 100000, "num_input_tokens_seen": 0, "num_train_epochs": 62, "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": 7587180589056000.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }