minilm-l12-h384-sst2-distilled
This model is a fine-tuned version of nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5417
- Accuracy: 0.9220
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: 0.0001400785945474408
- train_batch_size: 512
- eval_batch_size: 512
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2689 | 1.0 | 132 | 0.7102 | 0.8979 |
| 0.8295 | 2.0 | 264 | 0.5669 | 0.9117 |
| 0.5059 | 3.0 | 396 | 0.5545 | 0.9220 |
| 0.3722 | 4.0 | 528 | 0.5378 | 0.9209 |
| 0.2924 | 5.0 | 660 | 0.5417 | 0.9220 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.2+cu113
- Datasets 1.18.4
- Tokenizers 0.11.6
- Downloads last month
- 17
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.