{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0004044693867232924, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002022346933616462, "grad_norm": 0.3922646641731262, "learning_rate": 2e-05, "loss": 2.245, "step": 1 }, { "epoch": 0.0002022346933616462, "eval_loss": 2.176133394241333, "eval_runtime": 131.4289, "eval_samples_per_second": 7.921, "eval_steps_per_second": 7.921, "step": 1 }, { "epoch": 0.0004044693867232924, "grad_norm": 0.6289243698120117, "learning_rate": 4e-05, "loss": 2.22, "step": 2 }, { "epoch": 0.0004044693867232924, "eval_loss": 2.17583966255188, "eval_runtime": 131.5098, "eval_samples_per_second": 7.916, "eval_steps_per_second": 7.916, "step": 2 } ], "logging_steps": 1, "max_steps": 10, "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": 558968585846784.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }