<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
small-vanilla-target-glue-wnli
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 8.2398
- Accuracy: 0.0845
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6354 | 25.0 | 500 | 2.5362 | 0.0845 |
| 0.3043 | 50.0 | 1000 | 5.1175 | 0.0986 |
| 0.138 | 75.0 | 1500 | 6.7552 | 0.0986 |
| 0.0732 | 100.0 | 2000 | 7.6533 | 0.0986 |
| 0.0413 | 125.0 | 2500 | 8.2398 | 0.0845 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
