| { | |
| "best_metric": 0.1797216236591339, | |
| "best_model_checkpoint": "autotrain-vivi3n/checkpoint-1500", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 20.401409149169922, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.7642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 12.83076286315918, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.133, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 3.4568631649017334, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7359, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.5798301696777344, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7359, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 4.27333402633667, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6872, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 5.849865436553955, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6644, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 3.0048937797546387, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.667, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 6.366631031036377, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.6231, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 4.609536170959473, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.6099, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 4.420734882354736, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.563, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 2.8860912322998047, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.6232, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 4.6798577308654785, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5028, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 6.540982246398926, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.529, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 3.8343939781188965, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.5219, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2.1247823238372803, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4827, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.609323501586914, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.4975, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 5.313252925872803, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.5284, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 7.599594593048096, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4581, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 3.263301134109497, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.5126, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.882161617279053, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.397, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.852, | |
| "eval_auc": 0.943408, | |
| "eval_f1": 0.8366445916114791, | |
| "eval_loss": 0.32579681277275085, | |
| "eval_precision": 0.9334975369458128, | |
| "eval_recall": 0.758, | |
| "eval_runtime": 284.8907, | |
| "eval_samples_per_second": 3.51, | |
| "eval_steps_per_second": 0.221, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 4.248765468597412, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.3009, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 16.29542350769043, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.3521, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 4.925727367401123, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.3923, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 9.481324195861816, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3771, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 5.314146041870117, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.3731, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 5.7874531745910645, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.276, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 11.975399017333984, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.4218, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 3.5423085689544678, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2853, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 2.484663486480713, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.2941, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 8.482043266296387, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2908, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 11.303189277648926, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.2806, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 7.4056291580200195, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.2928, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 3.922528028488159, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3142, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 9.461620330810547, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.5345, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 3.0611841678619385, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.273, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 6.015491962432861, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3177, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 7.551340103149414, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.2656, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 13.884527206420898, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.3409, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.6236781477928162, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.222, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.7288349866867065, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2162, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.913, | |
| "eval_auc": 0.978072, | |
| "eval_f1": 0.9144542772861357, | |
| "eval_loss": 0.22896826267242432, | |
| "eval_precision": 0.8994197292069632, | |
| "eval_recall": 0.93, | |
| "eval_runtime": 285.1891, | |
| "eval_samples_per_second": 3.506, | |
| "eval_steps_per_second": 0.221, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 24.80970001220703, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.2816, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 3.5682404041290283, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1733, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 11.192222595214844, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 0.2307, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 3.6742281913757324, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1328, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 12.249692916870117, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.2833, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 9.88560676574707, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.2459, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 2.8054721355438232, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.2079, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 10.091593742370605, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2933, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 0.920978844165802, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.1921, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.0899479016661644, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1607, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 15.381816864013672, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.2516, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 0.061589837074279785, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.2309, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 7.775277614593506, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.312, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 5.62130880355835, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.2236, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 15.061668395996094, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.2173, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 4.630084991455078, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.2465, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 6.20747184753418, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.1715, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 1.773815393447876, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.2216, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 5.9370436668396, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.1786, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.292758464813232, | |
| "learning_rate": 0.0, | |
| "loss": 0.1342, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.935, | |
| "eval_auc": 0.986464, | |
| "eval_f1": 0.9353233830845771, | |
| "eval_loss": 0.1797216236591339, | |
| "eval_precision": 0.9306930693069307, | |
| "eval_recall": 0.94, | |
| "eval_runtime": 285.872, | |
| "eval_samples_per_second": 3.498, | |
| "eval_steps_per_second": 0.22, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 9.29903875375104e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |