<!-- 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-qqp-target-glue-mnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-qqp on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6551
- Accuracy: 0.7219
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 |
|---|---|---|---|---|
| 0.9185 | 0.04 | 500 | 0.8285 | 0.6395 |
| 0.8182 | 0.08 | 1000 | 0.7859 | 0.6628 |
| 0.7779 | 0.12 | 1500 | 0.7475 | 0.6761 |
| 0.7565 | 0.16 | 2000 | 0.7283 | 0.6913 |
| 0.7477 | 0.2 | 2500 | 0.7180 | 0.6929 |
| 0.7376 | 0.24 | 3000 | 0.7028 | 0.6964 |
| 0.7185 | 0.29 | 3500 | 0.6840 | 0.7137 |
| 0.7051 | 0.33 | 4000 | 0.6747 | 0.7190 |
| 0.6785 | 0.37 | 4500 | 0.6846 | 0.7192 |
| 0.685 | 0.41 | 5000 | 0.6551 | 0.7219 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
