{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0012598425196850393, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002519685039370079, "grad_norm": 7.116703033447266, "learning_rate": 1e-05, "loss": 2.7367, "step": 1 }, { "epoch": 0.0002519685039370079, "eval_loss": 2.8593077659606934, "eval_runtime": 128.7427, "eval_samples_per_second": 51.925, "eval_steps_per_second": 25.967, "step": 1 }, { "epoch": 0.0005039370078740158, "grad_norm": 7.5051984786987305, "learning_rate": 2e-05, "loss": 3.1469, "step": 2 }, { "epoch": 0.0005039370078740158, "eval_loss": 2.7861061096191406, "eval_runtime": 68.7197, "eval_samples_per_second": 97.279, "eval_steps_per_second": 48.647, "step": 2 }, { "epoch": 0.0007559055118110237, "grad_norm": 8.082169532775879, "learning_rate": 3e-05, "loss": 3.2166, "step": 3 }, { "epoch": 0.0010078740157480315, "grad_norm": 6.167407035827637, "learning_rate": 4e-05, "loss": 2.2379, "step": 4 }, { "epoch": 0.0010078740157480315, "eval_loss": 2.592325448989868, "eval_runtime": 69.9709, "eval_samples_per_second": 95.54, "eval_steps_per_second": 47.777, "step": 4 }, { "epoch": 0.0012598425196850393, "grad_norm": 6.184210777282715, "learning_rate": 5e-05, "loss": 2.5732, "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": 978955586764800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }