| { |
| "best_metric": 0.03481420502066612, |
| "best_model_checkpoint": "results_bert-base-french-europeana-cased/epoch20_bs64/checkpoint-48", |
| "epoch": 11.0, |
| "eval_steps": 500, |
| "global_step": 176, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.47372615337371826, |
| "learning_rate": 4.75e-05, |
| "loss": 0.3883, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accurracy": { |
| "accuracy": 0.9764285714285714 |
| }, |
| "eval_f1": [ |
| 0.9799147900182593, |
| 0.8114285714285714, |
| 1.0 |
| ], |
| "eval_loss": 0.08146535605192184, |
| "eval_precision": [ |
| 0.971049457177322, |
| 0.8875, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9889434889434889, |
| 0.7473684210526316, |
| 1.0 |
| ], |
| "eval_runtime": 4.1114, |
| "eval_samples_per_second": 12.161, |
| "eval_steps_per_second": 0.243, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.4207443296909332, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0566, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accurracy": { |
| "accuracy": 0.9878571428571429 |
| }, |
| "eval_f1": [ |
| 0.9895641497851443, |
| 0.91005291005291, |
| 1.0 |
| ], |
| "eval_loss": 0.04085615277290344, |
| "eval_precision": [ |
| 0.9889570552147239, |
| 0.9148936170212766, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9901719901719902, |
| 0.9052631578947369, |
| 1.0 |
| ], |
| "eval_runtime": 3.9019, |
| "eval_samples_per_second": 12.814, |
| "eval_steps_per_second": 0.256, |
| "step": 32 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.4004434049129486, |
| "learning_rate": 4.25e-05, |
| "loss": 0.0291, |
| "step": 48 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accurracy": { |
| "accuracy": 0.99 |
| }, |
| "eval_f1": [ |
| 0.991389913899139, |
| 0.9270833333333334, |
| 1.0 |
| ], |
| "eval_loss": 0.03481420502066612, |
| "eval_precision": [ |
| 0.9926108374384236, |
| 0.9175257731958762, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9901719901719902, |
| 0.9368421052631579, |
| 1.0 |
| ], |
| "eval_runtime": 3.5383, |
| "eval_samples_per_second": 14.131, |
| "eval_steps_per_second": 0.283, |
| "step": 48 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.3703693747520447, |
| "learning_rate": 4e-05, |
| "loss": 0.0169, |
| "step": 64 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accurracy": { |
| "accuracy": 0.9885714285714285 |
| }, |
| "eval_f1": [ |
| 0.9901719901719902, |
| 0.9157894736842105, |
| 1.0 |
| ], |
| "eval_loss": 0.03665424883365631, |
| "eval_precision": [ |
| 0.9901719901719902, |
| 0.9157894736842105, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9901719901719902, |
| 0.9157894736842105, |
| 1.0 |
| ], |
| "eval_runtime": 3.4858, |
| "eval_samples_per_second": 14.344, |
| "eval_steps_per_second": 0.287, |
| "step": 64 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.3292807936668396, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.0109, |
| "step": 80 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accurracy": { |
| "accuracy": 0.9878571428571429 |
| }, |
| "eval_f1": [ |
| 0.9894867037724181, |
| 0.9154228855721394, |
| 1.0 |
| ], |
| "eval_loss": 0.03761892020702362, |
| "eval_precision": [ |
| 0.9962640099626401, |
| 0.8679245283018868, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9828009828009828, |
| 0.968421052631579, |
| 1.0 |
| ], |
| "eval_runtime": 3.6656, |
| "eval_samples_per_second": 13.64, |
| "eval_steps_per_second": 0.273, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.17665812373161316, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0073, |
| "step": 96 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accurracy": { |
| "accuracy": 0.9878571428571429 |
| }, |
| "eval_f1": [ |
| 0.9895897121861604, |
| 0.9081081081081082, |
| 1.0 |
| ], |
| "eval_loss": 0.04045535624027252, |
| "eval_precision": [ |
| 0.9865689865689866, |
| 0.9333333333333333, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9926289926289926, |
| 0.8842105263157894, |
| 1.0 |
| ], |
| "eval_runtime": 3.1662, |
| "eval_samples_per_second": 15.792, |
| "eval_steps_per_second": 0.316, |
| "step": 96 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.46033716201782227, |
| "learning_rate": 3.2500000000000004e-05, |
| "loss": 0.0043, |
| "step": 112 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accurracy": { |
| "accuracy": 0.9885714285714285 |
| }, |
| "eval_f1": [ |
| 0.9901840490797545, |
| 0.9148936170212766, |
| 1.0 |
| ], |
| "eval_loss": 0.0450633242726326, |
| "eval_precision": [ |
| 0.9889705882352942, |
| 0.9247311827956989, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9914004914004914, |
| 0.9052631578947369, |
| 1.0 |
| ], |
| "eval_runtime": 3.1686, |
| "eval_samples_per_second": 15.78, |
| "eval_steps_per_second": 0.316, |
| "step": 112 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.7053983807563782, |
| "learning_rate": 3e-05, |
| "loss": 0.0029, |
| "step": 128 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accurracy": { |
| "accuracy": 0.9871428571428571 |
| }, |
| "eval_f1": [ |
| 0.9889570552147239, |
| 0.9042553191489362, |
| 1.0 |
| ], |
| "eval_loss": 0.055573731660842896, |
| "eval_precision": [ |
| 0.9877450980392157, |
| 0.9139784946236559, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9901719901719902, |
| 0.8947368421052632, |
| 1.0 |
| ], |
| "eval_runtime": 3.4353, |
| "eval_samples_per_second": 14.555, |
| "eval_steps_per_second": 0.291, |
| "step": 128 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.16288042068481445, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.0023, |
| "step": 144 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accurracy": { |
| "accuracy": 0.9892857142857143 |
| }, |
| "eval_f1": [ |
| 0.9908144519289651, |
| 0.918918918918919, |
| 1.0 |
| ], |
| "eval_loss": 0.05289832502603531, |
| "eval_precision": [ |
| 0.9877899877899878, |
| 0.9444444444444444, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9938574938574939, |
| 0.8947368421052632, |
| 1.0 |
| ], |
| "eval_runtime": 3.8415, |
| "eval_samples_per_second": 13.016, |
| "eval_steps_per_second": 0.26, |
| "step": 144 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.19770997762680054, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0021, |
| "step": 160 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accurracy": { |
| "accuracy": 0.9892857142857143 |
| }, |
| "eval_f1": [ |
| 0.990791896869245, |
| 0.9206349206349206, |
| 1.0 |
| ], |
| "eval_loss": 0.04967246204614639, |
| "eval_precision": [ |
| 0.9901840490797545, |
| 0.925531914893617, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9914004914004914, |
| 0.9157894736842105, |
| 1.0 |
| ], |
| "eval_runtime": 3.3345, |
| "eval_samples_per_second": 14.995, |
| "eval_steps_per_second": 0.3, |
| "step": 160 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.07273274660110474, |
| "learning_rate": 2.25e-05, |
| "loss": 0.0013, |
| "step": 176 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accurracy": { |
| "accuracy": 0.9921428571428571 |
| }, |
| "eval_f1": [ |
| 0.9932390903503381, |
| 0.9424083769633508, |
| 1.0 |
| ], |
| "eval_loss": 0.04350681230425835, |
| "eval_precision": [ |
| 0.993849938499385, |
| 0.9375, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9926289926289926, |
| 0.9473684210526315, |
| 1.0 |
| ], |
| "eval_runtime": 3.3327, |
| "eval_samples_per_second": 15.003, |
| "eval_steps_per_second": 0.3, |
| "step": 176 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 320, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 168415447860000.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
