<!-- 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-snli-target-glue-qqp
This model is a fine-tuned version of muhtasham/small-mlm-snli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3292
- Accuracy: 0.8524
- F1: 0.8149
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 |
|---|---|---|---|---|---|
| 0.4793 | 0.04 | 500 | 0.4220 | 0.7894 | 0.7450 |
| 0.4207 | 0.09 | 1000 | 0.3887 | 0.8126 | 0.7699 |
| 0.4041 | 0.13 | 1500 | 0.3707 | 0.8238 | 0.7766 |
| 0.3862 | 0.18 | 2000 | 0.3711 | 0.8236 | 0.7888 |
| 0.3801 | 0.22 | 2500 | 0.3596 | 0.8346 | 0.7965 |
| 0.3603 | 0.26 | 3000 | 0.3442 | 0.8414 | 0.8010 |
| 0.3607 | 0.31 | 3500 | 0.3301 | 0.8515 | 0.8018 |
| 0.3523 | 0.35 | 4000 | 0.3314 | 0.8497 | 0.8074 |
| 0.3585 | 0.4 | 4500 | 0.3257 | 0.8517 | 0.8108 |
| 0.345 | 0.44 | 5000 | 0.3292 | 0.8524 | 0.8149 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
