{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.04757548032936871, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0036596523330283625, "eval_loss": 6.844988822937012, "eval_runtime": 6.9069, "eval_samples_per_second": 16.65, "eval_steps_per_second": 8.397, "step": 1 }, { "epoch": 0.018298261665141813, "grad_norm": 11.751487731933594, "learning_rate": 5e-05, "loss": 6.8396, "step": 5 }, { "epoch": 0.036596523330283626, "grad_norm": 8.099217414855957, "learning_rate": 0.0001, "loss": 4.2657, "step": 10 }, { "epoch": 0.036596523330283626, "eval_loss": 1.4936703443527222, "eval_runtime": 6.9534, "eval_samples_per_second": 16.539, "eval_steps_per_second": 8.341, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2142169800376320.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }