Downloads · 30 days
34
8% of all-time downloads
tiny-mlm-glue-sst2-from-scratch-custom-tokenizer-target-glue-cola
muhtasham/tiny-mlm-glue-sst2-from-scratch-custom-tokenizer-target-glue-cola
tiny-mlm-glue-sst2-from-scratch-custom-tokenizer-target-glue-cola is a text classification model from muhtasham. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
402
Public
Repo size
99.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin10 MB · 95%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 13, 2023
- Updated
- Jan 13, 2023
- SHA
- 9a458852
Try a prompt
Model card
From the Hugging Face model README
<!-- 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-sst2-from-scratch-custom-tokenizer-target-glue-cola
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7800
- Matthews Correlation: 0.0949
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 | Matthews Correlation |
|---|---|---|---|---|
| 0.6129 | 1.87 | 500 | 0.6207 | 0.0 |
| 0.6072 | 3.73 | 1000 | 0.6192 | 0.0 |
| 0.5953 | 5.6 | 1500 | 0.6407 | 0.0 |
| 0.5446 | 7.46 | 2000 | 0.6964 | 0.0228 |
| 0.5043 | 9.33 | 2500 | 0.7292 | 0.0739 |
| 0.4922 | 11.19 | 3000 | 0.7188 | 0.1001 |
| 0.4682 | 13.06 | 3500 | 0.7339 | 0.0767 |
| 0.4561 | 14.93 | 4000 | 0.7683 | 0.0636 |
| 0.4414 | 16.79 | 4500 | 0.7800 | 0.0949 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Jan 13, 2023
- Updated
- Jan 13, 2023