tiny-mlm-glue-cola-custom-tokenizer-target-glue-rte
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: 1.5050
- Accuracy: 0.5487
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 |
---|---|---|---|---|
0.6536 | 6.41 | 500 | 0.7250 | 0.5596 |
0.5285 | 12.82 | 1000 | 0.8611 | 0.5668 |
0.3876 | 19.23 | 1500 | 1.0801 | 0.5487 |
0.2712 | 25.64 | 2000 | 1.2735 | 0.5560 |
0.1877 | 32.05 | 2500 | 1.5050 | 0.5487 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.