<!-- 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-base-uncased-sentiment-finetuned-memes-30epochs
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: 1.8839
- Accuracy: 0.8365
- Precision: 0.8373
- Recall: 0.8365
- F1: 0.8368
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.4774 | 1.0 | 2147 | 0.4463 | 0.7453 | 0.7921 | 0.7453 | 0.7468 |
0.4036 | 2.0 | 4294 | 0.5419 | 0.7835 | 0.8072 | 0.7835 | 0.7858 |
0.3163 | 3.0 | 6441 | 0.6776 | 0.7982 | 0.7970 | 0.7982 | 0.7954 |
0.2613 | 4.0 | 8588 | 0.6988 | 0.7966 | 0.7953 | 0.7966 | 0.7956 |
0.229 | 5.0 | 10735 | 0.8523 | 0.8003 | 0.8033 | 0.8003 | 0.8013 |
0.1893 | 6.0 | 12882 | 1.0472 | 0.8056 | 0.8166 | 0.8056 | 0.8074 |
0.1769 | 7.0 | 15029 | 1.0321 | 0.8150 | 0.8193 | 0.8150 | 0.8161 |
0.1648 | 8.0 | 17176 | 1.1623 | 0.8129 | 0.8159 | 0.8129 | 0.8138 |
0.1366 | 9.0 | 19323 | 1.1932 | 0.8255 | 0.8257 | 0.8255 | 0.8256 |
0.1191 | 10.0 | 21470 | 1.2308 | 0.8349 | 0.8401 | 0.8349 | 0.8361 |
0.1042 | 11.0 | 23617 | 1.3166 | 0.8297 | 0.8288 | 0.8297 | 0.8281 |
0.0847 | 12.0 | 25764 | 1.3542 | 0.8286 | 0.8278 | 0.8286 | 0.8280 |
0.0785 | 13.0 | 27911 | 1.3925 | 0.8291 | 0.8293 | 0.8291 | 0.8292 |
0.0674 | 14.0 | 30058 | 1.4191 | 0.8255 | 0.8307 | 0.8255 | 0.8267 |
0.0694 | 15.0 | 32205 | 1.5601 | 0.8255 | 0.8281 | 0.8255 | 0.8263 |
0.0558 | 16.0 | 34352 | 1.6110 | 0.8265 | 0.8302 | 0.8265 | 0.8275 |
0.045 | 17.0 | 36499 | 1.5730 | 0.8270 | 0.8303 | 0.8270 | 0.8280 |
0.0436 | 18.0 | 38646 | 1.6081 | 0.8365 | 0.8361 | 0.8365 | 0.8363 |
0.028 | 19.0 | 40793 | 1.5569 | 0.8375 | 0.8371 | 0.8375 | 0.8373 |
0.0262 | 20.0 | 42940 | 1.6976 | 0.8286 | 0.8324 | 0.8286 | 0.8296 |
0.0183 | 21.0 | 45087 | 1.6368 | 0.8333 | 0.8354 | 0.8333 | 0.8340 |
0.0225 | 22.0 | 47234 | 1.7570 | 0.8318 | 0.8357 | 0.8318 | 0.8328 |
0.0118 | 23.0 | 49381 | 1.7233 | 0.8360 | 0.8369 | 0.8360 | 0.8363 |
0.0152 | 24.0 | 51528 | 1.8027 | 0.8360 | 0.8371 | 0.8360 | 0.8364 |
0.0079 | 25.0 | 53675 | 1.7908 | 0.8412 | 0.8423 | 0.8412 | 0.8416 |
0.0102 | 26.0 | 55822 | 1.8247 | 0.8344 | 0.8339 | 0.8344 | 0.8341 |
0.0111 | 27.0 | 57969 | 1.8123 | 0.8391 | 0.8394 | 0.8391 | 0.8392 |
0.0078 | 28.0 | 60116 | 1.8630 | 0.8354 | 0.8352 | 0.8354 | 0.8353 |
0.0058 | 29.0 | 62263 | 1.8751 | 0.8339 | 0.8343 | 0.8339 | 0.8341 |
0.0028 | 30.0 | 64410 | 1.8839 | 0.8365 | 0.8373 | 0.8365 | 0.8368 |
Framework versions
- Transformers 4.13.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 1.15.2.dev0
- Tokenizers 0.10.1