{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.08, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008, "grad_norm": 7.379425525665283, "learning_rate": 0.0, "loss": 4.016258239746094, "step": 1 }, { "epoch": 0.016, "grad_norm": 8.28126335144043, "learning_rate": 4e-05, "loss": 4.1329755783081055, "step": 2 }, { "epoch": 0.024, "grad_norm": 5.840158939361572, "learning_rate": 8e-05, "loss": 3.7547378540039062, "step": 3 }, { "epoch": 0.032, "grad_norm": 6.3198065757751465, "learning_rate": 0.00012, "loss": 3.216219902038574, "step": 4 }, { "epoch": 0.04, "grad_norm": 12.44980239868164, "learning_rate": 0.00016, "loss": 2.5023694038391113, "step": 5 }, { "epoch": 0.048, "grad_norm": 5.22922945022583, "learning_rate": 0.0002, "loss": 1.930384874343872, "step": 6 }, { "epoch": 0.056, "grad_norm": 14.052867889404297, "learning_rate": 0.00016, "loss": 1.3705148696899414, "step": 7 }, { "epoch": 0.064, "grad_norm": 5.280429363250732, "learning_rate": 0.00012, "loss": 1.0065242052078247, "step": 8 }, { "epoch": 0.072, "grad_norm": 2.942521333694458, "learning_rate": 8e-05, "loss": 0.7536088228225708, "step": 9 }, { "epoch": 0.08, "grad_norm": 2.898214817047119, "learning_rate": 4e-05, "loss": 0.6234063506126404, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 405816829575168.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }