Downloads · 30 days
7
12% of all-time downloads
saransh_biogpt_custom
saransharora96/saransh_biogpt_custom
saransh_biogpt_custom is a token classification model from saransharora96. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
58
Public
Repo size
8.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.4 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- gpt2
- Access
- Public
- Created
- May 13, 2023
- Updated
- May 13, 2023
- SHA
- a30cef4b
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. -->
saransh_biogpt_custom
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2376
- Precision: 0.3702
- Recall: 0.2097
- F1: 0.2677
- Accuracy: 0.9300
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 418 | 0.2439 | 0.3401 | 0.1315 | 0.1896 | 0.9284 |
| 0.2906 | 2.0 | 836 | 0.2326 | 0.3448 | 0.1956 | 0.2496 | 0.9293 |
| 0.2348 | 3.0 | 1254 | 0.2376 | 0.3702 | 0.2097 | 0.2677 | 0.9300 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- gpt2
- Created
- May 13, 2023
- Updated
- May 13, 2023