Downloads · 30 days
13
39% of all-time downloads
MatSciBERT_BIOMAT_NER
judithrosell/MatSciBERT_BIOMAT_NER
MatSciBERT_BIOMAT_NER is a machine learning model from judithrosell. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
33
Public
Parameters
109M
4.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors437 MB · 100%
At a glance
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Aug 28, 2024
- Updated
- Aug 28, 2024
- SHA
- da707da7
Base models
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. -->
MatSciBERT_BIOMAT_NER
This model is a fine-tuned version of m3rg-iitd/matscibert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4484
- Precision: 0.9532
- Recall: 0.9448
- F1: 0.9490
- Accuracy: 0.9449
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 422 | 0.2540 | 0.9489 | 0.9421 | 0.9455 | 0.9408 |
| 0.1742 | 2.0 | 844 | 0.2844 | 0.9512 | 0.9422 | 0.9466 | 0.9413 |
| 0.051 | 3.0 | 1266 | 0.3248 | 0.9515 | 0.9436 | 0.9475 | 0.9433 |
| 0.024 | 4.0 | 1688 | 0.3364 | 0.9515 | 0.9448 | 0.9481 | 0.9439 |
| 0.014 | 5.0 | 2110 | 0.4033 | 0.9503 | 0.9419 | 0.9461 | 0.9417 |
| 0.0073 | 6.0 | 2532 | 0.4042 | 0.9532 | 0.9433 | 0.9482 | 0.9438 |
| 0.0073 | 7.0 | 2954 | 0.4115 | 0.9531 | 0.9443 | 0.9487 | 0.9443 |
| 0.0047 | 8.0 | 3376 | 0.4141 | 0.9527 | 0.9447 | 0.9487 | 0.9445 |
| 0.0033 | 9.0 | 3798 | 0.4392 | 0.9536 | 0.9450 | 0.9493 | 0.9450 |
| 0.0018 | 10.0 | 4220 | 0.4484 | 0.9532 | 0.9448 | 0.9490 | 0.9449 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- bert
- License
- mit
- Created
- Aug 28, 2024
- Updated
- Aug 28, 2024