{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00015710096355257646, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.236698785085882e-05, "grad_norm": 0.4392659366130829, "learning_rate": 2e-05, "loss": 0.5208, "step": 1 }, { "epoch": 5.236698785085882e-05, "eval_loss": 0.6633045673370361, "eval_runtime": 722.4901, "eval_samples_per_second": 11.13, "eval_steps_per_second": 5.565, "step": 1 }, { "epoch": 0.00010473397570171764, "grad_norm": 0.5572344660758972, "learning_rate": 4e-05, "loss": 0.6158, "step": 2 }, { "epoch": 0.00015710096355257646, "grad_norm": 0.6260502338409424, "learning_rate": 6e-05, "loss": 0.6381, "step": 3 }, { "epoch": 0.00015710096355257646, "eval_loss": 0.6599137187004089, "eval_runtime": 722.6318, "eval_samples_per_second": 11.127, "eval_steps_per_second": 5.564, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1231436170395648.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }