{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.040160642570281124, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008032128514056224, "grad_norm": 2.2730464935302734, "learning_rate": 1e-05, "loss": 25.0153, "step": 1 }, { "epoch": 0.008032128514056224, "eval_loss": 1.5288861989974976, "eval_runtime": 22.6713, "eval_samples_per_second": 9.263, "eval_steps_per_second": 4.631, "step": 1 }, { "epoch": 0.01606425702811245, "grad_norm": 2.2744619846343994, "learning_rate": 2e-05, "loss": 23.5088, "step": 2 }, { "epoch": 0.01606425702811245, "eval_loss": 1.5253138542175293, "eval_runtime": 7.5769, "eval_samples_per_second": 27.716, "eval_steps_per_second": 13.858, "step": 2 }, { "epoch": 0.024096385542168676, "grad_norm": 2.448141098022461, "learning_rate": 3e-05, "loss": 23.0411, "step": 3 }, { "epoch": 0.0321285140562249, "grad_norm": 1.915059208869934, "learning_rate": 4e-05, "loss": 25.1573, "step": 4 }, { "epoch": 0.0321285140562249, "eval_loss": 1.5223687887191772, "eval_runtime": 7.6013, "eval_samples_per_second": 27.627, "eval_steps_per_second": 13.813, "step": 4 }, { "epoch": 0.040160642570281124, "grad_norm": 4.761684894561768, "learning_rate": 5e-05, "loss": 24.8143, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4641935339814912.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }