canine_sent_2304v1
This model is a fine-tuned version of google/canine-s on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
- Accuracy: 1.0
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0218 | 1.0 | 781 | 0.0051 | 0.9531 | 0.9434 | 0.9482 | 0.9980 |
| 0.0059 | 2.0 | 1562 | 0.0028 | 0.9712 | 0.9714 | 0.9713 | 0.9989 |
| 0.0043 | 3.0 | 2343 | 0.0018 | 0.9733 | 0.9980 | 0.9855 | 0.9994 |
| 0.0021 | 4.0 | 3124 | 0.0010 | 0.9873 | 0.9991 | 0.9932 | 0.9997 |
| 0.0018 | 5.0 | 3905 | 0.0005 | 0.9952 | 0.9984 | 0.9968 | 0.9998 |
| 0.0012 | 6.0 | 4686 | 0.0002 | 0.9988 | 0.9986 | 0.9987 | 0.9999 |
| 0.0007 | 7.0 | 5467 | 0.0001 | 0.9989 | 0.9986 | 0.9988 | 1.0000 |
| 0.0007 | 8.0 | 6248 | 0.0001 | 0.9998 | 0.9991 | 0.9995 | 1.0000 |
| 0.0004 | 9.0 | 7029 | 0.0000 | 0.9998 | 1.0 | 0.9999 | 1.0000 |
| 0.0004 | 10.0 | 7810 | 0.0000 | 0.9998 | 0.9995 | 0.9996 | 1.0000 |
| 0.0003 | 11.0 | 8591 | 0.0001 | 0.9996 | 0.9998 | 0.9997 | 1.0000 |
| 0.0002 | 12.0 | 9372 | 0.0000 | 1.0 | 0.9998 | 0.9999 | 1.0000 |
| 0.0002 | 13.0 | 10153 | 0.0000 | 1.0 | 0.9998 | 0.9999 | 1.0000 |
| 0.0001 | 14.0 | 10934 | 0.0000 | 1.0 | 0.9998 | 0.9999 | 1.0000 |
| 0.0001 | 15.0 | 11715 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- 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.