uniBERT.distilBERT.3
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: 1.7293
- Accuracy: (0.4772117962466488,)
- F1: (0.4693132851587397,)
- Precision: (0.5442146665454255,)
- Recall: 0.4772
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: 64
- 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 | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
2.9412 | 1.0 | 210 | 2.7539 | (0.19302949061662197,) | (0.1603618689364134,) | (0.1948027475862202,) | 0.1930 |
2.1163 | 2.0 | 420 | 2.1123 | (0.30831099195710454,) | (0.2886576454762518,) | (0.34306886958718397,) | 0.3083 |
1.5605 | 3.0 | 630 | 1.9332 | (0.35924932975871315,) | (0.3408370919837017,) | (0.4437777540758143,) | 0.3592 |
1.2042 | 4.0 | 840 | 1.7857 | (0.4262734584450402,) | (0.4114641689723971,) | (0.5423496541710991,) | 0.4263 |
0.9317 | 5.0 | 1050 | 1.7584 | (0.4262734584450402,) | (0.41517951297641825,) | (0.5270241126881486,) | 0.4263 |
0.7497 | 6.0 | 1260 | 1.7334 | (0.46380697050938335,) | (0.4616472194616382,) | (0.5561767348377945,) | 0.4638 |
0.6484 | 7.0 | 1470 | 1.7148 | (0.48257372654155495,) | (0.47743545933365816,) | (0.5507046992541056,) | 0.4826 |
0.5396 | 8.0 | 1680 | 1.7341 | (0.47989276139410186,) | (0.4727261312495505,) | (0.5529949943706518,) | 0.4799 |
0.4599 | 9.0 | 1890 | 1.7252 | (0.4772117962466488,) | (0.47031578431963555,) | (0.5474190199916943,) | 0.4772 |
0.427 | 10.0 | 2100 | 1.7293 | (0.4772117962466488,) | (0.4693132851587397,) | (0.5442146665454255,) | 0.4772 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2