<!-- 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-mlm-glue-mnli-target-glue-mnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6497
- Accuracy: 0.7259
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 |
|---|---|---|---|---|
| 0.9145 | 0.04 | 500 | 0.8234 | 0.6373 |
| 0.8123 | 0.08 | 1000 | 0.7786 | 0.6628 |
| 0.7745 | 0.12 | 1500 | 0.7489 | 0.6756 |
| 0.7496 | 0.16 | 2000 | 0.7311 | 0.6878 |
| 0.7424 | 0.2 | 2500 | 0.7205 | 0.6921 |
| 0.7325 | 0.24 | 3000 | 0.7007 | 0.7007 |
| 0.7126 | 0.29 | 3500 | 0.6780 | 0.7131 |
| 0.7007 | 0.33 | 4000 | 0.6652 | 0.7189 |
| 0.6755 | 0.37 | 4500 | 0.6737 | 0.7249 |
| 0.6803 | 0.41 | 5000 | 0.6497 | 0.7259 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
