| { | |
| "best_global_step": 500, | |
| "best_metric": 2.075254201889038, | |
| "best_model_checkpoint": "/content/drive/MyDrive/MedGemma_Chinese_QA/models/checkpoints/checkpoint-500", | |
| "epoch": 0.1936108422071636, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03872216844143272, | |
| "grad_norm": 15.748984336853027, | |
| "learning_rate": 3.960000000000001e-05, | |
| "loss": 51.8035, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07744433688286544, | |
| "grad_norm": 26.268953323364258, | |
| "learning_rate": 7.960000000000001e-05, | |
| "loss": 40.493, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11616650532429816, | |
| "grad_norm": 19.70706558227539, | |
| "learning_rate": 0.00011960000000000001, | |
| "loss": 35.7189, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15488867376573087, | |
| "grad_norm": 19.33815574645996, | |
| "learning_rate": 0.0001596, | |
| "loss": 34.6084, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1936108422071636, | |
| "grad_norm": 12.032870292663574, | |
| "learning_rate": 0.0001996, | |
| "loss": 33.1728, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1936108422071636, | |
| "eval_loss": 2.075254201889038, | |
| "eval_runtime": 6327.4485, | |
| "eval_samples_per_second": 0.767, | |
| "eval_steps_per_second": 0.767, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7749, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "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": 2.568310007267328e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |