<!-- 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-multilingual-cased-distilbert_mlm-20230603
This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9199
- Loss: 0.3297
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: 20
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
No log | 1.0 | 130 | 0.9035 | 0.3341 |
No log | 2.0 | 260 | 0.9288 | 0.2137 |
No log | 3.0 | 390 | 0.9150 | 0.3078 |
0.3659 | 4.0 | 520 | 0.9301 | 0.3323 |
0.3659 | 5.0 | 650 | 0.8896 | 0.4231 |
0.3659 | 6.0 | 780 | 0.9414 | 0.2144 |
0.3659 | 7.0 | 910 | 0.9333 | 0.2529 |
0.3935 | 8.0 | 1040 | 0.9192 | 0.2802 |
0.3935 | 9.0 | 1170 | 0.9274 | 0.3097 |
0.3935 | 10.0 | 1300 | 0.9182 | 0.3077 |
0.3935 | 11.0 | 1430 | 0.9153 | 0.2983 |
0.3835 | 12.0 | 1560 | 0.9136 | 0.2692 |
0.3835 | 13.0 | 1690 | 0.9524 | 0.1930 |
0.3835 | 14.0 | 1820 | 0.9412 | 0.2278 |
0.3835 | 15.0 | 1950 | 0.9657 | 0.1305 |
0.3327 | 16.0 | 2080 | 0.8980 | 0.3051 |
0.3327 | 17.0 | 2210 | 0.9485 | 0.1348 |
0.3327 | 18.0 | 2340 | 0.9381 | 0.2765 |
0.3327 | 19.0 | 2470 | 0.9477 | 0.2165 |
0.3238 | 20.0 | 2600 | 0.9199 | 0.3297 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3