| { | |
| "best_metric": 0.12875927984714508, | |
| "best_model_checkpoint": "/home/jcanete/ft-data/all_results/ner/albeto_base_10/epochs_4_bs_32_lr_5e-5/checkpoint-700", | |
| "epoch": 4.0, | |
| "global_step": 1044, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.9292493244579186, | |
| "eval_f1": 0.6192774836499534, | |
| "eval_loss": 0.2619832754135132, | |
| "eval_precision": 0.6041318547774571, | |
| "eval_recall": 0.6352020444018528, | |
| "eval_runtime": 1.8554, | |
| "eval_samples_per_second": 1032.641, | |
| "eval_steps_per_second": 32.337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9522177552230936, | |
| "eval_f1": 0.7341891045710708, | |
| "eval_loss": 0.1654893010854721, | |
| "eval_precision": 0.7198772064466615, | |
| "eval_recall": 0.7490816163552149, | |
| "eval_runtime": 1.7972, | |
| "eval_samples_per_second": 1066.105, | |
| "eval_steps_per_second": 33.385, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.9579516245963224, | |
| "eval_f1": 0.7919559492458702, | |
| "eval_loss": 0.149013951420784, | |
| "eval_precision": 0.7913875598086124, | |
| "eval_recall": 0.7925251557259224, | |
| "eval_runtime": 1.8699, | |
| "eval_samples_per_second": 1024.659, | |
| "eval_steps_per_second": 32.087, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_accuracy": 0.9607032228300271, | |
| "eval_f1": 0.7946535126103907, | |
| "eval_loss": 0.13737879693508148, | |
| "eval_precision": 0.7916930881420419, | |
| "eval_recall": 0.7976361603577703, | |
| "eval_runtime": 1.8043, | |
| "eval_samples_per_second": 1061.881, | |
| "eval_steps_per_second": 33.253, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.6149425287356323e-05, | |
| "loss": 0.2123, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.9636525406972912, | |
| "eval_f1": 0.8209348781462246, | |
| "eval_loss": 0.12951940298080444, | |
| "eval_precision": 0.8213943076431084, | |
| "eval_recall": 0.8204759623063408, | |
| "eval_runtime": 1.7875, | |
| "eval_samples_per_second": 1071.873, | |
| "eval_steps_per_second": 33.566, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_accuracy": 0.9627463257101431, | |
| "eval_f1": 0.8149384187524832, | |
| "eval_loss": 0.13606947660446167, | |
| "eval_precision": 0.8108791903858318, | |
| "eval_recall": 0.8190384922536336, | |
| "eval_runtime": 1.798, | |
| "eval_samples_per_second": 1065.622, | |
| "eval_steps_per_second": 33.37, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_accuracy": 0.962762802346273, | |
| "eval_f1": 0.8076046822216985, | |
| "eval_loss": 0.12875927984714508, | |
| "eval_precision": 0.7946815089672232, | |
| "eval_recall": 0.8209551189905766, | |
| "eval_runtime": 1.8023, | |
| "eval_samples_per_second": 1063.059, | |
| "eval_steps_per_second": 33.29, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.9635866341527713, | |
| "eval_f1": 0.8158271094867312, | |
| "eval_loss": 0.1313953548669815, | |
| "eval_precision": 0.811699604743083, | |
| "eval_recall": 0.8199968056221051, | |
| "eval_runtime": 1.7921, | |
| "eval_samples_per_second": 1069.118, | |
| "eval_steps_per_second": 33.48, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.9627957556185329, | |
| "eval_f1": 0.8106307021023402, | |
| "eval_loss": 0.13798536360263824, | |
| "eval_precision": 0.805327868852459, | |
| "eval_recall": 0.8160038332534739, | |
| "eval_runtime": 1.8024, | |
| "eval_samples_per_second": 1063.055, | |
| "eval_steps_per_second": 33.29, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 2.2030651340996167e-06, | |
| "loss": 0.0591, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_accuracy": 0.9642292229618401, | |
| "eval_f1": 0.818637194879542, | |
| "eval_loss": 0.13375717401504517, | |
| "eval_precision": 0.8150728309056364, | |
| "eval_recall": 0.8222328701485385, | |
| "eval_runtime": 1.8609, | |
| "eval_samples_per_second": 1029.628, | |
| "eval_steps_per_second": 32.243, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1044, | |
| "total_flos": 139056718739136.0, | |
| "train_loss": 0.13201307291272044, | |
| "train_runtime": 54.4964, | |
| "train_samples_per_second": 610.976, | |
| "train_steps_per_second": 19.157 | |
| } | |
| ], | |
| "max_steps": 1044, | |
| "num_train_epochs": 4, | |
| "total_flos": 139056718739136.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |