{ "best_metric": 1.6234142780303955, "best_model_checkpoint": "/kaggle/working/checkpoint-20", "epoch": 3.0, "eval_steps": 10, "global_step": 27, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.1111111111111112, "grad_norm": 0.022207504138350487, "learning_rate": 0.00012592592592592592, "loss": 2.058, "step": 10 }, { "epoch": 1.1111111111111112, "eval_loss": 1.769914984703064, "eval_runtime": 34.8115, "eval_samples_per_second": 1.034, "eval_steps_per_second": 0.144, "step": 10 }, { "epoch": 2.2222222222222223, "grad_norm": 0.022052476182579994, "learning_rate": 5.185185185185185e-05, "loss": 1.6674, "step": 20 }, { "epoch": 2.2222222222222223, "eval_loss": 1.6234142780303955, "eval_runtime": 34.7607, "eval_samples_per_second": 1.036, "eval_steps_per_second": 0.144, "step": 20 } ], "logging_steps": 10, "max_steps": 27, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": true }, "attributes": {} } }, "total_flos": 7214144522747904.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }