fnet-large-finetuned-cola-copy3
This model is a fine-tuned version of google/fnet-large on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6554
- Matthews Correlation: 0.0
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: 0.0001
- train_batch_size: 4
- 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 | Matthews Correlation |
|---|---|---|---|---|
| 0.6408 | 1.0 | 2138 | 0.7329 | 0.0 |
| 0.6589 | 2.0 | 4276 | 0.6311 | 0.0 |
| 0.6467 | 3.0 | 6414 | 0.6554 | 0.0 |
Framework versions
- Transformers 4.11.0.dev0
- Pytorch 1.9.0
- Datasets 1.12.1
- Tokenizers 0.10.3
- Downloads last month
- 16
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.