<!-- 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. -->
bert-finetuned-sst2
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4586
- Precision: 0.9388
- Recall: 0.9404
- F1: 0.9396
- Accuracy: 0.9466
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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1277 | 1.0 | 4210 | 0.2173 | 0.9321 | 0.9348 | 0.9335 | 0.9439 |
0.075 | 2.0 | 8420 | 0.2417 | 0.9355 | 0.9375 | 0.9365 | 0.9455 |
0.0445 | 3.0 | 12630 | 0.2835 | 0.9367 | 0.9374 | 0.9370 | 0.9441 |
0.0318 | 4.0 | 16840 | 0.3141 | 0.9359 | 0.9375 | 0.9367 | 0.9448 |
0.0208 | 5.0 | 21050 | 0.3496 | 0.9383 | 0.9391 | 0.9387 | 0.9463 |
0.0158 | 6.0 | 25260 | 0.3693 | 0.9375 | 0.9390 | 0.9383 | 0.9462 |
0.01 | 7.0 | 29470 | 0.4158 | 0.9361 | 0.9384 | 0.9373 | 0.9454 |
0.0058 | 8.0 | 33680 | 0.4270 | 0.9374 | 0.9389 | 0.9382 | 0.9456 |
0.0031 | 9.0 | 37890 | 0.4540 | 0.9376 | 0.9387 | 0.9381 | 0.9455 |
0.0015 | 10.0 | 42100 | 0.4586 | 0.9388 | 0.9404 | 0.9396 | 0.9466 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1