Downloads · 30 days
5
24% of all-time downloads
MLMA_Lab_8_GPT_model
shubhanmathur/MLMA_Lab_8_GPT_model
MLMA_Lab_8_GPT_model is a token classification model from shubhanmathur. 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
21
Public
Parameters
347M
4.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- gpt2
- Access
- Public
- Created
- Apr 13, 2024
- Updated
- Apr 14, 2024
- SHA
- 444fa7cb
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. -->
MLMA_Lab_8_GPT_model
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1509
- Precision: 0.4333
- Recall: 0.5197
- F1: 0.4726
- Accuracy: 0.9564
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 |
|---|---|---|---|---|---|---|---|
| 0.3275 | 1.0 | 679 | 0.1747 | 0.2975 | 0.4460 | 0.3569 | 0.9449 |
| 0.169 | 2.0 | 1358 | 0.1661 | 0.3892 | 0.4956 | 0.4360 | 0.9510 |
| 0.0994 | 3.0 | 2037 | 0.1509 | 0.4333 | 0.5197 | 0.4726 | 0.9564 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.0
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- gpt2
- Created
- Apr 13, 2024
- Updated
- Apr 14, 2024