| { | |
| "best_metric": 0.8835274542429284, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-masakhaner-ibo/checkpoint-3000", | |
| "epoch": 57.142857142857146, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy_score": 0.973508883248731, | |
| "eval_f1": 0.8375927452596867, | |
| "eval_loss": 0.0908978134393692, | |
| "eval_precision": 0.8287112561174551, | |
| "eval_recall": 0.8466666666666667, | |
| "eval_runtime": 4.4899, | |
| "eval_samples_per_second": 71.271, | |
| "eval_steps_per_second": 8.909, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_accuracy_score": 0.9760469543147208, | |
| "eval_f1": 0.8602329450915143, | |
| "eval_loss": 0.10517112910747528, | |
| "eval_precision": 0.8588039867109635, | |
| "eval_recall": 0.8616666666666667, | |
| "eval_runtime": 4.4923, | |
| "eval_samples_per_second": 71.233, | |
| "eval_steps_per_second": 8.904, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 4.865771812080537e-05, | |
| "loss": 0.1423, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "eval_accuracy_score": 0.9762055837563451, | |
| "eval_f1": 0.8692810457516339, | |
| "eval_loss": 0.10657743364572525, | |
| "eval_precision": 0.8525641025641025, | |
| "eval_recall": 0.8866666666666667, | |
| "eval_runtime": 4.4983, | |
| "eval_samples_per_second": 71.139, | |
| "eval_steps_per_second": 8.892, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "eval_accuracy_score": 0.9747779187817259, | |
| "eval_f1": 0.8621553884711779, | |
| "eval_loss": 0.14751985669136047, | |
| "eval_precision": 0.864321608040201, | |
| "eval_recall": 0.86, | |
| "eval_runtime": 4.4901, | |
| "eval_samples_per_second": 71.268, | |
| "eval_steps_per_second": 8.908, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 4.697986577181208e-05, | |
| "loss": 0.006, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "eval_accuracy_score": 0.9733502538071066, | |
| "eval_f1": 0.8581138487680544, | |
| "eval_loss": 0.1495266854763031, | |
| "eval_precision": 0.8752166377816292, | |
| "eval_recall": 0.8416666666666667, | |
| "eval_runtime": 4.4785, | |
| "eval_samples_per_second": 71.453, | |
| "eval_steps_per_second": 8.932, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "eval_accuracy_score": 0.9743020304568528, | |
| "eval_f1": 0.8580912863070539, | |
| "eval_loss": 0.13109683990478516, | |
| "eval_precision": 0.8545454545454545, | |
| "eval_recall": 0.8616666666666667, | |
| "eval_runtime": 4.4894, | |
| "eval_samples_per_second": 71.279, | |
| "eval_steps_per_second": 8.91, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy_score": 0.975729695431472, | |
| "eval_f1": 0.8702791461412152, | |
| "eval_loss": 0.12132257223129272, | |
| "eval_precision": 0.8576051779935275, | |
| "eval_recall": 0.8833333333333333, | |
| "eval_runtime": 4.4948, | |
| "eval_samples_per_second": 71.193, | |
| "eval_steps_per_second": 8.899, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 4.530201342281879e-05, | |
| "loss": 0.0039, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy_score": 0.9727157360406091, | |
| "eval_f1": 0.8521594684385383, | |
| "eval_loss": 0.14406903088092804, | |
| "eval_precision": 0.8493377483443708, | |
| "eval_recall": 0.855, | |
| "eval_runtime": 4.488, | |
| "eval_samples_per_second": 71.301, | |
| "eval_steps_per_second": 8.913, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "eval_accuracy_score": 0.9760469543147208, | |
| "eval_f1": 0.8736401673640167, | |
| "eval_loss": 0.13323232531547546, | |
| "eval_precision": 0.8773109243697479, | |
| "eval_recall": 0.87, | |
| "eval_runtime": 4.4884, | |
| "eval_samples_per_second": 71.295, | |
| "eval_steps_per_second": 8.912, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 4.36241610738255e-05, | |
| "loss": 0.003, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "eval_accuracy_score": 0.9768401015228426, | |
| "eval_f1": 0.8747940691927514, | |
| "eval_loss": 0.1382114142179489, | |
| "eval_precision": 0.8648208469055375, | |
| "eval_recall": 0.885, | |
| "eval_runtime": 4.4872, | |
| "eval_samples_per_second": 71.313, | |
| "eval_steps_per_second": 8.914, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "eval_accuracy_score": 0.9774746192893401, | |
| "eval_f1": 0.8793969849246231, | |
| "eval_loss": 0.1348169445991516, | |
| "eval_precision": 0.8838383838383839, | |
| "eval_recall": 0.875, | |
| "eval_runtime": 4.4981, | |
| "eval_samples_per_second": 71.141, | |
| "eval_steps_per_second": 8.893, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy_score": 0.9762055837563451, | |
| "eval_f1": 0.8757297748123437, | |
| "eval_loss": 0.16189880669116974, | |
| "eval_precision": 0.8764607679465777, | |
| "eval_recall": 0.875, | |
| "eval_runtime": 4.491, | |
| "eval_samples_per_second": 71.253, | |
| "eval_steps_per_second": 8.907, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 4.194630872483222e-05, | |
| "loss": 0.002, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 37.14, | |
| "eval_accuracy_score": 0.9741434010152284, | |
| "eval_f1": 0.8702928870292886, | |
| "eval_loss": 0.18092279136180878, | |
| "eval_precision": 0.8739495798319328, | |
| "eval_recall": 0.8666666666666667, | |
| "eval_runtime": 4.4888, | |
| "eval_samples_per_second": 71.289, | |
| "eval_steps_per_second": 8.911, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy_score": 0.9768401015228426, | |
| "eval_f1": 0.8835672997522708, | |
| "eval_loss": 0.14144042134284973, | |
| "eval_precision": 0.8756137479541735, | |
| "eval_recall": 0.8916666666666667, | |
| "eval_runtime": 4.4955, | |
| "eval_samples_per_second": 71.183, | |
| "eval_steps_per_second": 8.898, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 4.026845637583892e-05, | |
| "loss": 0.0022, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "eval_accuracy_score": 0.9779505076142132, | |
| "eval_f1": 0.8835274542429284, | |
| "eval_loss": 0.1496778428554535, | |
| "eval_precision": 0.8820598006644518, | |
| "eval_recall": 0.885, | |
| "eval_runtime": 4.4823, | |
| "eval_samples_per_second": 71.392, | |
| "eval_steps_per_second": 8.924, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "eval_accuracy_score": 0.9755710659898477, | |
| "eval_f1": 0.8616404308202154, | |
| "eval_loss": 0.1561731994152069, | |
| "eval_precision": 0.85667215815486, | |
| "eval_recall": 0.8666666666666667, | |
| "eval_runtime": 4.4881, | |
| "eval_samples_per_second": 71.3, | |
| "eval_steps_per_second": 8.913, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "eval_accuracy_score": 0.9766814720812182, | |
| "eval_f1": 0.8719665271966527, | |
| "eval_loss": 0.1539183408021927, | |
| "eval_precision": 0.8756302521008403, | |
| "eval_recall": 0.8683333333333333, | |
| "eval_runtime": 4.4822, | |
| "eval_samples_per_second": 71.393, | |
| "eval_steps_per_second": 8.924, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3.859060402684564e-05, | |
| "loss": 0.0014, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 51.43, | |
| "eval_accuracy_score": 0.9744606598984772, | |
| "eval_f1": 0.8673894912427023, | |
| "eval_loss": 0.1729230135679245, | |
| "eval_precision": 0.8681135225375626, | |
| "eval_recall": 0.8666666666666667, | |
| "eval_runtime": 4.4847, | |
| "eval_samples_per_second": 71.354, | |
| "eval_steps_per_second": 8.919, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 54.29, | |
| "eval_accuracy_score": 0.9743020304568528, | |
| "eval_f1": 0.8600167644593462, | |
| "eval_loss": 0.1779366433620453, | |
| "eval_precision": 0.8650927487352446, | |
| "eval_recall": 0.855, | |
| "eval_runtime": 4.4776, | |
| "eval_samples_per_second": 71.467, | |
| "eval_steps_per_second": 8.933, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "learning_rate": 3.6912751677852356e-05, | |
| "loss": 0.0024, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "eval_accuracy_score": 0.9758883248730964, | |
| "eval_f1": 0.8710217755443885, | |
| "eval_loss": 0.14653384685516357, | |
| "eval_precision": 0.8754208754208754, | |
| "eval_recall": 0.8666666666666667, | |
| "eval_runtime": 4.4684, | |
| "eval_samples_per_second": 71.614, | |
| "eval_steps_per_second": 8.952, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "step": 4000, | |
| "total_flos": 1.668681362767104e+16, | |
| "train_loss": 0.020399520963430406, | |
| "train_runtime": 4498.3257, | |
| "train_samples_per_second": 106.706, | |
| "train_steps_per_second": 3.335 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 215, | |
| "total_flos": 1.668681362767104e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |