{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.003478865889719951, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00017394329448599757, "eval_loss": 31.39523696899414, "eval_runtime": 15.6242, "eval_samples_per_second": 154.952, "eval_steps_per_second": 77.508, "step": 1 }, { "epoch": 0.0005218298834579927, "grad_norm": 1378.8846435546875, "learning_rate": 6e-05, "loss": 101.6594, "step": 3 }, { "epoch": 0.0010436597669159853, "grad_norm": 2315.408935546875, "learning_rate": 0.00012, "loss": 139.6225, "step": 6 }, { "epoch": 0.0013915463558879806, "eval_loss": 31.306568145751953, "eval_runtime": 14.1121, "eval_samples_per_second": 171.555, "eval_steps_per_second": 85.813, "step": 8 }, { "epoch": 0.0015654896503739782, "grad_norm": 1939.8433837890625, "learning_rate": 0.00018, "loss": 125.2086, "step": 9 }, { "epoch": 0.0020873195338319706, "grad_norm": 1662.098388671875, "learning_rate": 0.00019510565162951537, "loss": 115.1138, "step": 12 }, { "epoch": 0.0026091494172899633, "grad_norm": 1860.805419921875, "learning_rate": 0.00017071067811865476, "loss": 104.8186, "step": 15 }, { "epoch": 0.002783092711775961, "eval_loss": 31.02450180053711, "eval_runtime": 15.2933, "eval_samples_per_second": 158.305, "eval_steps_per_second": 79.185, "step": 16 }, { "epoch": 0.0031309793007479564, "grad_norm": 1440.878662109375, "learning_rate": 0.00013090169943749476, "loss": 104.8424, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 44686450360320.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }