<!-- 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-mnli
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: 0.9264
- Accuracy: 0.5644
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 |
|---|---|---|---|---|
| 1.0999 | 0.04 | 500 | 1.0987 | 0.3975 |
| 1.0483 | 0.08 | 1000 | 1.0515 | 0.4310 |
| 1.0189 | 0.12 | 1500 | 0.9948 | 0.4982 |
| 0.9952 | 0.16 | 2000 | 0.9831 | 0.5156 |
| 0.9854 | 0.2 | 2500 | 0.9795 | 0.5052 |
| 0.9812 | 0.24 | 3000 | 0.9790 | 0.5196 |
| 0.9707 | 0.29 | 3500 | 0.9570 | 0.5227 |
| 0.9575 | 0.33 | 4000 | 0.9498 | 0.5371 |
| 0.9503 | 0.37 | 4500 | 0.9443 | 0.5468 |
| 0.9427 | 0.41 | 5000 | 0.9264 | 0.5644 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
