| { |
| "best_global_step": 2000, |
| "best_metric": 0.9388425925925926, |
| "best_model_checkpoint": "myocardial_pubmedbert_mps_final_v3/checkpoint-2000", |
| "epoch": 0.37037037037037035, |
| "eval_steps": 1000, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.018518518518518517, |
| "grad_norm": 2.475142478942871, |
| "learning_rate": 9.9e-08, |
| "loss": 0.1439, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.037037037037037035, |
| "grad_norm": 1.806380271911621, |
| "learning_rate": 1.99e-07, |
| "loss": 0.1511, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.05555555555555555, |
| "grad_norm": 1.5451908111572266, |
| "learning_rate": 2.9899999999999996e-07, |
| "loss": 0.1491, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.07407407407407407, |
| "grad_norm": 2.704113483428955, |
| "learning_rate": 3.99e-07, |
| "loss": 0.153, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.09259259259259259, |
| "grad_norm": 4.833273887634277, |
| "learning_rate": 4.99e-07, |
| "loss": 0.149, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 1.2810375690460205, |
| "learning_rate": 5.989999999999999e-07, |
| "loss": 0.1582, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.12962962962962962, |
| "grad_norm": 9.05034065246582, |
| "learning_rate": 6.989999999999999e-07, |
| "loss": 0.1711, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.14814814814814814, |
| "grad_norm": 7.097633361816406, |
| "learning_rate": 7.99e-07, |
| "loss": 0.1419, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.16666666666666666, |
| "grad_norm": 10.607206344604492, |
| "learning_rate": 8.99e-07, |
| "loss": 0.1298, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.18518518518518517, |
| "grad_norm": 1.5295910835266113, |
| "learning_rate": 9.989999999999999e-07, |
| "loss": 0.1401, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.18518518518518517, |
| "eval_accuracy": 0.9386111111111111, |
| "eval_loss": 0.1337883323431015, |
| "eval_runtime": 906.5981, |
| "eval_samples_per_second": 47.651, |
| "eval_steps_per_second": 1.489, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2037037037037037, |
| "grad_norm": 7.718695163726807, |
| "learning_rate": 9.98132075471698e-07, |
| "loss": 0.1463, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 2.2934257984161377, |
| "learning_rate": 9.962452830188678e-07, |
| "loss": 0.1505, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.24074074074074073, |
| "grad_norm": 4.265007495880127, |
| "learning_rate": 9.943584905660378e-07, |
| "loss": 0.1451, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.25925925925925924, |
| "grad_norm": 8.984698295593262, |
| "learning_rate": 9.924716981132075e-07, |
| "loss": 0.1412, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 6.165067672729492, |
| "learning_rate": 9.905849056603772e-07, |
| "loss": 0.1354, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 14.949434280395508, |
| "learning_rate": 9.886981132075472e-07, |
| "loss": 0.1305, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.3148148148148148, |
| "grad_norm": 5.017131805419922, |
| "learning_rate": 9.86811320754717e-07, |
| "loss": 0.147, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 6.54106330871582, |
| "learning_rate": 9.849245283018867e-07, |
| "loss": 0.1435, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.35185185185185186, |
| "grad_norm": 10.726076126098633, |
| "learning_rate": 9.830377358490567e-07, |
| "loss": 0.1347, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.37037037037037035, |
| "grad_norm": 7.49448299407959, |
| "learning_rate": 9.811509433962264e-07, |
| "loss": 0.1539, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.37037037037037035, |
| "eval_accuracy": 0.9388425925925926, |
| "eval_loss": 0.13230355083942413, |
| "eval_runtime": 839.9501, |
| "eval_samples_per_second": 51.432, |
| "eval_steps_per_second": 1.607, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 54000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "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": 1.6840165883904e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
