{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00023535410987114363, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 7.845136995704788e-05, "grad_norm": 0.9127047061920166, "learning_rate": 2e-05, "loss": 2.1072, "step": 1 }, { "epoch": 7.845136995704788e-05, "eval_loss": 2.1771984100341797, "eval_runtime": 364.9344, "eval_samples_per_second": 14.709, "eval_steps_per_second": 7.355, "step": 1 }, { "epoch": 0.00015690273991409576, "grad_norm": 1.0036420822143555, "learning_rate": 4e-05, "loss": 2.4194, "step": 2 }, { "epoch": 0.00023535410987114363, "grad_norm": 1.1165186166763306, "learning_rate": 6e-05, "loss": 2.1131, "step": 3 }, { "epoch": 0.00023535410987114363, "eval_loss": 2.1711175441741943, "eval_runtime": 363.6197, "eval_samples_per_second": 14.763, "eval_steps_per_second": 7.381, "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": 1108895921602560.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }