Downloads · 30 days
37
32% of all-time downloads
tiny-mlm-glue-rte-from-scratch-custom-tokenizer-target-glue-sst2
muhtasham/tiny-mlm-glue-rte-from-scratch-custom-tokenizer-target-glue-sst2
tiny-mlm-glue-rte-from-scratch-custom-tokenizer-target-glue-sst2 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
116
Public
Repo size
151 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin13.7 MB · 95%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 13, 2023
- Updated
- Jan 13, 2023
- SHA
- 27943d38
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-rte-from-scratch-custom-tokenizer-target-glue-sst2
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-rte-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4372
- Accuracy: 0.8291
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 |
|---|---|---|---|---|
| 0.6881 | 0.24 | 500 | 0.6939 | 0.5092 |
| 0.6816 | 0.48 | 1000 | 0.6838 | 0.5860 |
| 0.5821 | 0.71 | 1500 | 0.5562 | 0.7144 |
| 0.442 | 0.95 | 2000 | 0.4730 | 0.7752 |
| 0.3829 | 1.19 | 2500 | 0.4535 | 0.7890 |
| 0.3528 | 1.43 | 3000 | 0.4293 | 0.8119 |
| 0.3371 | 1.66 | 3500 | 0.4224 | 0.8211 |
| 0.3249 | 1.9 | 4000 | 0.4300 | 0.8131 |
| 0.3072 | 2.14 | 4500 | 0.4298 | 0.8200 |
| 0.2876 | 2.38 | 5000 | 0.4372 | 0.8291 |
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