<!-- 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. -->
tiny-mlm-glue-mnli-target-glue-mnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8010
- Accuracy: 0.6426
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0743 | 0.04 | 500 | 1.0281 | 0.4738 |
| 1.0045 | 0.08 | 1000 | 0.9576 | 0.5522 |
| 0.9565 | 0.12 | 1500 | 0.9155 | 0.5802 |
| 0.929 | 0.16 | 2000 | 0.8997 | 0.5936 |
| 0.9205 | 0.2 | 2500 | 0.8868 | 0.6011 |
| 0.9127 | 0.24 | 3000 | 0.8733 | 0.6066 |
| 0.8972 | 0.29 | 3500 | 0.8659 | 0.6121 |
| 0.8908 | 0.33 | 4000 | 0.8527 | 0.6202 |
| 0.8747 | 0.37 | 4500 | 0.8507 | 0.6200 |
| 0.8778 | 0.41 | 5000 | 0.8418 | 0.6254 |
| 0.869 | 0.45 | 5500 | 0.8373 | 0.6262 |
| 0.8647 | 0.49 | 6000 | 0.8339 | 0.6318 |
| 0.8677 | 0.53 | 6500 | 0.8268 | 0.6310 |
| 0.8576 | 0.57 | 7000 | 0.8269 | 0.6323 |
| 0.852 | 0.61 | 7500 | 0.8126 | 0.6396 |
| 0.8525 | 0.65 | 8000 | 0.8119 | 0.6399 |
| 0.8441 | 0.69 | 8500 | 0.8230 | 0.6319 |
| 0.8492 | 0.73 | 9000 | 0.7975 | 0.6486 |
| 0.8394 | 0.77 | 9500 | 0.8088 | 0.6373 |
| 0.8294 | 0.81 | 10000 | 0.7949 | 0.6460 |
| 0.8341 | 0.86 | 10500 | 0.8010 | 0.6426 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
