BERT_B07
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2269
- Precision: 0.6290
- Recall: 0.6789
- F1: 0.6530
- Accuracy: 0.9317
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: 4e-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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.4974 | 1.0 | 46 | 0.3685 | 0.5057 | 0.4568 | 0.4800 | 0.8932 |
0.2353 | 2.0 | 92 | 0.2460 | 0.5996 | 0.6272 | 0.6130 | 0.9252 |
0.17 | 3.0 | 138 | 0.2264 | 0.5949 | 0.6421 | 0.6176 | 0.9286 |
0.1429 | 4.0 | 184 | 0.2272 | 0.6083 | 0.6720 | 0.6386 | 0.9305 |
0.1252 | 5.0 | 230 | 0.2269 | 0.6290 | 0.6789 | 0.6530 | 0.9317 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.