{ "best_metric": 1.4144253730773926, "best_model_checkpoint": "/kaggle/working/checkpoint-30", "epoch": 3.3333333333333335, "eval_steps": 10, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.1111111111111112, "grad_norm": 0.022457197308540344, "learning_rate": 0.0001925925925925926, "loss": 2.0406, "step": 10 }, { "epoch": 1.1111111111111112, "eval_loss": 1.729261875152588, "eval_runtime": 34.8953, "eval_samples_per_second": 1.032, "eval_steps_per_second": 0.143, "step": 10 }, { "epoch": 2.2222222222222223, "grad_norm": 0.018787898123264313, "learning_rate": 0.0001851851851851852, "loss": 1.6016, "step": 20 }, { "epoch": 2.2222222222222223, "eval_loss": 1.5362553596496582, "eval_runtime": 34.8752, "eval_samples_per_second": 1.032, "eval_steps_per_second": 0.143, "step": 20 }, { "epoch": 3.3333333333333335, "grad_norm": 0.021070128306746483, "learning_rate": 0.00017777777777777779, "loss": 1.3937, "step": 30 }, { "epoch": 3.3333333333333335, "eval_loss": 1.4144253730773926, "eval_runtime": 34.9429, "eval_samples_per_second": 1.03, "eval_steps_per_second": 0.143, "step": 30 } ], "logging_steps": 10, "max_steps": 270, "num_input_tokens_seen": 0, "num_train_epochs": 30, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8007449233588224.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }