| { |
| "best_global_step": 100, |
| "best_metric": 0.01389834564179182, |
| "best_model_checkpoint": "/teamspace/studios/this_studio/DATN/output/medgemma_finetuned/checkpoint-100", |
| "epoch": 0.38910505836575876, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.019455252918287938, |
| "grad_norm": 3.0237326622009277, |
| "learning_rate": 1.777777777777778e-06, |
| "loss": 0.8809, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.038910505836575876, |
| "grad_norm": 2.4512810707092285, |
| "learning_rate": 4e-06, |
| "loss": 0.8569, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.058365758754863814, |
| "grad_norm": 1.5967055559158325, |
| "learning_rate": 6.222222222222222e-06, |
| "loss": 0.7725, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.07782101167315175, |
| "grad_norm": 1.2497001886367798, |
| "learning_rate": 8.444444444444446e-06, |
| "loss": 0.6516, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09727626459143969, |
| "grad_norm": 1.2455090284347534, |
| "learning_rate": 1.0666666666666667e-05, |
| "loss": 0.5238, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.11673151750972763, |
| "grad_norm": 1.361525535583496, |
| "learning_rate": 1.2888888888888889e-05, |
| "loss": 0.3777, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.13618677042801555, |
| "grad_norm": 1.6556775569915771, |
| "learning_rate": 1.511111111111111e-05, |
| "loss": 0.2116, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1556420233463035, |
| "grad_norm": 0.6078555583953857, |
| "learning_rate": 1.7333333333333332e-05, |
| "loss": 0.0794, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.17509727626459143, |
| "grad_norm": 0.31556975841522217, |
| "learning_rate": 1.9555555555555557e-05, |
| "loss": 0.0343, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.19455252918287938, |
| "grad_norm": 0.23063282668590546, |
| "learning_rate": 2.177777777777778e-05, |
| "loss": 0.0227, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2140077821011673, |
| "grad_norm": 0.10897089540958405, |
| "learning_rate": 2.4e-05, |
| "loss": 0.0159, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.23346303501945526, |
| "grad_norm": 0.08667729049921036, |
| "learning_rate": 2.6222222222222226e-05, |
| "loss": 0.0155, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2529182879377432, |
| "grad_norm": 0.07056345790624619, |
| "learning_rate": 2.8444444444444447e-05, |
| "loss": 0.0133, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.2723735408560311, |
| "grad_norm": 0.119380883872509, |
| "learning_rate": 3.066666666666666e-05, |
| "loss": 0.0113, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2918287937743191, |
| "grad_norm": 0.10328345745801926, |
| "learning_rate": 3.288888888888889e-05, |
| "loss": 0.0074, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.311284046692607, |
| "grad_norm": 0.08840714395046234, |
| "learning_rate": 3.511111111111111e-05, |
| "loss": 0.0069, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.33073929961089493, |
| "grad_norm": 0.1998119205236435, |
| "learning_rate": 3.733333333333334e-05, |
| "loss": 0.0069, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.35019455252918286, |
| "grad_norm": 0.08085718750953674, |
| "learning_rate": 3.9555555555555556e-05, |
| "loss": 0.0072, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.36964980544747084, |
| "grad_norm": 0.10597972571849823, |
| "learning_rate": 4.177777777777778e-05, |
| "loss": 0.0072, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.38910505836575876, |
| "grad_norm": 0.04654397815465927, |
| "learning_rate": 4.4e-05, |
| "loss": 0.0065, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.38910505836575876, |
| "eval_loss": 0.01389834564179182, |
| "eval_runtime": 174.9649, |
| "eval_samples_per_second": 2.915, |
| "eval_steps_per_second": 0.732, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1799, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 30, |
| "early_stopping_threshold": 0.001 |
| }, |
| "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": 6.810966969647155e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
