<!-- 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-cola-custom-tokenizer-target-glue-mrpc
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1575
- Accuracy: 0.7083
- F1: 0.8027
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 | F1 |
|---|---|---|---|---|---|
| 0.596 | 4.35 | 500 | 0.5737 | 0.7034 | 0.8045 |
| 0.5008 | 8.7 | 1000 | 0.6054 | 0.7132 | 0.8104 |
| 0.4191 | 13.04 | 1500 | 0.6542 | 0.7034 | 0.7939 |
| 0.332 | 17.39 | 2000 | 0.7210 | 0.7157 | 0.7993 |
| 0.2612 | 21.74 | 2500 | 0.8037 | 0.7206 | 0.81 |
| 0.2045 | 26.09 | 3000 | 0.8845 | 0.7083 | 0.7993 |
| 0.1645 | 30.43 | 3500 | 0.9976 | 0.7181 | 0.8080 |
| 0.1301 | 34.78 | 4000 | 1.1575 | 0.7083 | 0.8027 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
