{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9884169884169884, "eval_steps": 500, "global_step": 32, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.3088803088803089, "grad_norm": 58237.08984375, "learning_rate": 1.4375e-05, "loss": 2.3251, "step": 10 }, { "epoch": 0.6177606177606177, "grad_norm": 45477.11328125, "learning_rate": 8.125000000000001e-06, "loss": 2.3583, "step": 20 }, { "epoch": 0.9266409266409267, "grad_norm": 46869.8359375, "learning_rate": 1.8750000000000003e-06, "loss": 2.4309, "step": 30 } ], "logging_steps": 10, "max_steps": 32, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1858151833927680.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }