xtremedistil-l6-h256-company-names
This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on the nbroad/company_names dataset. It achieves the following results on the evaluation set:
- Loss: 0.0789
- Precision: 0.6999
- Recall: 0.7154
- F1: 0.7076
- Accuracy: 0.9702
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: 8e-05
- train_batch_size: 48
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1052 | 1.0 | 2126 | 0.0854 | 0.6824 | 0.6605 | 0.6713 | 0.9678 |
| 0.0724 | 2.0 | 4252 | 0.0814 | 0.6925 | 0.7042 | 0.6983 | 0.9696 |
| 0.0778 | 3.0 | 6378 | 0.0789 | 0.6999 | 0.7154 | 0.7076 | 0.9702 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.14.1