{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.19598236158745713, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.019598236158745713, "grad_norm": 3.5889872960343827, "learning_rate": 6.451612903225806e-06, "loss": 0.7126, "step": 10 }, { "epoch": 0.039196472317491425, "grad_norm": 2.4561369076384403, "learning_rate": 1.2903225806451613e-05, "loss": 0.5561, "step": 20 }, { "epoch": 0.05879470847623714, "grad_norm": 1.809708978535045, "learning_rate": 1.935483870967742e-05, "loss": 0.5326, "step": 30 }, { "epoch": 0.07839294463498285, "grad_norm": 1.6860179044060182, "learning_rate": 1.9995913677815705e-05, "loss": 0.5588, "step": 40 }, { "epoch": 0.09799118079372857, "grad_norm": 1.7787790392866307, "learning_rate": 1.9981792407143988e-05, "loss": 0.5589, "step": 50 }, { "epoch": 0.11758941695247428, "grad_norm": 1.6477457194954939, "learning_rate": 1.995759998385789e-05, "loss": 0.5743, "step": 60 }, { "epoch": 0.13718765311122, "grad_norm": 1.8012664207541251, "learning_rate": 1.9923360816959016e-05, "loss": 0.5821, "step": 70 }, { "epoch": 0.1567858892699657, "grad_norm": 1.7511422652788236, "learning_rate": 1.9879109452134283e-05, "loss": 0.5781, "step": 80 }, { "epoch": 0.1763841254287114, "grad_norm": 1.6767395409558863, "learning_rate": 1.9824890536900917e-05, "loss": 0.5844, "step": 90 }, { "epoch": 0.19598236158745713, "grad_norm": 1.6991325268847768, "learning_rate": 1.9760758775559275e-05, "loss": 0.5747, "step": 100 } ], "logging_steps": 10, "max_steps": 1020, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 13062560808960.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }