<!-- 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-mnli-from-scratch-custom-tokenizer-target-glue-mrpc
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6245
- Accuracy: 0.6201
- F1: 0.6990
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 |
|---|---|---|---|---|---|
| 0.6321 | 4.35 | 500 | 0.6107 | 0.6838 | 0.8122 |
| 0.5481 | 8.7 | 1000 | 0.6208 | 0.6936 | 0.7941 |
| 0.3207 | 13.04 | 1500 | 0.8799 | 0.6275 | 0.696 |
| 0.1738 | 17.39 | 2000 | 1.2027 | 0.6348 | 0.7162 |
| 0.1133 | 21.74 | 2500 | 1.6245 | 0.6201 | 0.6990 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
