{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.009907120743034056, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004953560371517028, "grad_norm": 6.830551624298096, "learning_rate": 1e-05, "loss": 5.9707, "step": 1 }, { "epoch": 0.004953560371517028, "eval_loss": 5.818502426147461, "eval_runtime": 93.4642, "eval_samples_per_second": 3.638, "eval_steps_per_second": 1.819, "step": 1 }, { "epoch": 0.009907120743034056, "grad_norm": 7.741116046905518, "learning_rate": 2e-05, "loss": 6.2652, "step": 2 }, { "epoch": 0.009907120743034056, "eval_loss": 5.703013896942139, "eval_runtime": 10.2181, "eval_samples_per_second": 33.274, "eval_steps_per_second": 16.637, "step": 2 } ], "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": false }, "attributes": {} } }, "total_flos": 1641914893860864.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }