canine-c-finetuned-sst2
This model is a fine-tuned version of google/canine-c on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6025
- Accuracy: 0.8486
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: 4.9121586874695155e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3415 | 1.0 | 2105 | 0.4196 | 0.8280 |
| 0.2265 | 2.0 | 4210 | 0.4924 | 0.8211 |
| 0.1439 | 3.0 | 6315 | 0.5726 | 0.8337 |
| 0.0974 | 4.0 | 8420 | 0.6025 | 0.8486 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
- Downloads last month
- 15
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.