<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
DistilBERT-TC1000new-10epochs
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1041
- Recall: {'recall': 0.98}
- Precision: {'precision': 0.9803125}
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Recall | Precision |
|---|---|---|---|---|---|
| 1.0487 | 0.35 | 20 | 0.9344 | {'recall': 0.65} | {'precision': 0.7268554095045501} |
| 0.8188 | 0.7 | 40 | 0.5972 | {'recall': 0.94} | {'precision': 0.9445447154471545} |
| 0.4832 | 1.05 | 60 | 0.3348 | {'recall': 0.92} | {'precision': 0.9216638655462185} |
| 0.2652 | 1.4 | 80 | 0.1883 | {'recall': 0.95} | {'precision': 0.9504561403508772} |
| 0.1615 | 1.75 | 100 | 0.1381 | {'recall': 0.94} | {'precision': 0.9407058791178574} |
| 0.128 | 2.11 | 120 | 0.0923 | {'recall': 0.98} | {'precision': 0.981025641025641} |
| 0.0625 | 2.46 | 140 | 0.1014 | {'recall': 0.97} | {'precision': 0.9700347222222223} |
| 0.0318 | 2.81 | 160 | 0.0715 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0187 | 3.16 | 180 | 0.0968 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0106 | 3.51 | 200 | 0.0843 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0268 | 3.86 | 220 | 0.0860 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0074 | 4.21 | 240 | 0.1058 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0194 | 4.56 | 260 | 0.1108 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0056 | 4.91 | 280 | 0.1048 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0044 | 5.26 | 300 | 0.1034 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0063 | 5.61 | 320 | 0.1034 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0032 | 5.96 | 340 | 0.1033 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0031 | 6.32 | 360 | 0.1039 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.003 | 6.67 | 380 | 0.1012 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0027 | 7.02 | 400 | 0.1013 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0026 | 7.37 | 420 | 0.1019 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0024 | 7.72 | 440 | 0.1043 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0023 | 8.07 | 460 | 0.1060 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0022 | 8.42 | 480 | 0.1052 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0022 | 8.77 | 500 | 0.1038 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0021 | 9.12 | 520 | 0.1037 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0021 | 9.47 | 540 | 0.1038 | {'recall': 0.98} | {'precision': 0.9803125} |
| 0.0021 | 9.82 | 560 | 0.1041 | {'recall': 0.98} | {'precision': 0.9803125} |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
