metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: distil-bert-imeocap
results: []
distil-bert-imeocap
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8186
- F1: 0.6341
- Precision: 0.6365
- Recall: 0.6365
- Accuracy: 0.6365
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
---|---|---|---|---|---|---|---|
0.1961 | 1.0 | 74 | 1.6080 | 0.6314 | 0.6285 | 0.6385 | 0.6385 |
0.1845 | 2.0 | 148 | 1.7125 | 0.6298 | 0.6317 | 0.6385 | 0.6385 |
0.1717 | 3.0 | 222 | 1.9402 | 0.6226 | 0.6364 | 0.6385 | 0.6385 |
0.176 | 4.0 | 296 | 1.8028 | 0.6169 | 0.6253 | 0.6192 | 0.6192 |
0.1679 | 5.0 | 370 | 1.6948 | 0.6243 | 0.6285 | 0.625 | 0.625 |
0.168 | 6.0 | 444 | 1.8304 | 0.6317 | 0.6336 | 0.6385 | 0.6385 |
0.1617 | 7.0 | 518 | 1.7457 | 0.6286 | 0.6310 | 0.6308 | 0.6308 |
0.1677 | 8.0 | 592 | 1.8071 | 0.6422 | 0.6382 | 0.65 | 0.65 |
0.171 | 9.0 | 666 | 1.8177 | 0.6323 | 0.6326 | 0.6385 | 0.6385 |
0.1683 | 10.0 | 740 | 1.8265 | 0.6347 | 0.6370 | 0.6365 | 0.6365 |
0.1808 | 11.0 | 814 | 1.7734 | 0.6304 | 0.6365 | 0.6308 | 0.6308 |
0.1757 | 12.0 | 888 | 1.7727 | 0.6244 | 0.6296 | 0.6231 | 0.6231 |
0.1897 | 13.0 | 962 | 1.8449 | 0.6374 | 0.6377 | 0.6404 | 0.6404 |
0.1674 | 14.0 | 1036 | 1.8244 | 0.6455 | 0.6462 | 0.6481 | 0.6481 |
0.1746 | 15.0 | 1110 | 1.8186 | 0.6341 | 0.6365 | 0.6365 | 0.6365 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2