tiny-mlm-snli-target-glue-mrpc
This model is a fine-tuned version of muhtasham/tiny-mlm-snli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1053
- Accuracy: 0.6814
- F1: 0.7601
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 | F1 |
|---|---|---|---|---|---|
| 0.5879 | 4.35 | 500 | 0.5553 | 0.7279 | 0.8189 |
| 0.4565 | 8.7 | 1000 | 0.5597 | 0.7598 | 0.8388 |
| 0.3208 | 13.04 | 1500 | 0.6303 | 0.7426 | 0.8217 |
| 0.2133 | 17.39 | 2000 | 0.7777 | 0.7230 | 0.8094 |
| 0.137 | 21.74 | 2500 | 1.1053 | 0.6814 | 0.7601 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2