<!-- 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-cola-from-scratch-custom-tokenizer-target-glue-mrpc
This model is a fine-tuned version of muhtasham/small-mlm-glue-cola-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9820
- Accuracy: 0.6029
- F1: 0.6966
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 |
|---|---|---|---|---|---|
| 0.5678 | 4.35 | 500 | 0.7008 | 0.5931 | 0.6527 |
| 0.3356 | 8.7 | 1000 | 1.1777 | 0.5564 | 0.6205 |
| 0.1971 | 13.04 | 1500 | 1.5307 | 0.5441 | 0.6092 |
| 0.1051 | 17.39 | 2000 | 1.8466 | 0.6495 | 0.7487 |
| 0.0696 | 21.74 | 2500 | 2.7232 | 0.6005 | 0.6965 |
| 0.0559 | 26.09 | 3000 | 3.0538 | 0.5956 | 0.6904 |
| 0.0423 | 30.43 | 3500 | 2.9820 | 0.6029 | 0.6966 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
