Downloads · 30 days
31
30% of all-time downloads
tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qqp
muhtasham/tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qqp
tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qqp 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
103
Public
Repo size
117 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin10.6 MB · 95%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 13, 2023
- Updated
- Jan 13, 2023
- SHA
- 0cf1a0d3
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-mrpc-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5311
- Accuracy: 0.7402
- F1: 0.5973
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 |
|---|---|---|---|---|---|
| 0.6429 | 0.04 | 500 | 0.6232 | 0.6395 | 0.3481 |
| 0.6149 | 0.09 | 1000 | 0.6025 | 0.6619 | 0.4427 |
| 0.5929 | 0.13 | 1500 | 0.5800 | 0.6870 | 0.5779 |
| 0.5688 | 0.18 | 2000 | 0.5620 | 0.7075 | 0.5454 |
| 0.5597 | 0.22 | 2500 | 0.5503 | 0.7218 | 0.5681 |
| 0.5477 | 0.26 | 3000 | 0.5432 | 0.7283 | 0.5902 |
| 0.5467 | 0.31 | 3500 | 0.5388 | 0.7322 | 0.5946 |
| 0.541 | 0.35 | 4000 | 0.5357 | 0.7350 | 0.6098 |
| 0.543 | 0.4 | 4500 | 0.5331 | 0.7348 | 0.6141 |
| 0.5377 | 0.44 | 5000 | 0.5311 | 0.7402 | 0.5973 |
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