Downloads · 30 days
12
33% of all-time downloads
MatSciBERT_BIOMAT_NER2
judithrosell/MatSciBERT_BIOMAT_NER2
MatSciBERT_BIOMAT_NER2 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
36
Public
Parameters
109M
8.7 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 29, 2024
- Updated
- Aug 30, 2024
- SHA
- 385273ec
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_NER2
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: 0.5936
- Precision: 0.9555
- Recall: 0.9490
- F1: 0.9523
- Accuracy: 0.9426
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 |
|---|---|---|---|---|---|---|---|
| 0.0537 | 1.0 | 1171 | 0.3242 | 0.9568 | 0.9456 | 0.9512 | 0.9406 |
| 0.0163 | 2.0 | 2342 | 0.3726 | 0.9578 | 0.9499 | 0.9538 | 0.9447 |
| 0.0054 | 3.0 | 3513 | 0.4411 | 0.9565 | 0.9496 | 0.9530 | 0.9432 |
| 0.0029 | 4.0 | 4684 | 0.4982 | 0.9562 | 0.9480 | 0.9521 | 0.9420 |
| 0.0017 | 5.0 | 5855 | 0.5276 | 0.9548 | 0.9472 | 0.9510 | 0.9404 |
| 0.001 | 6.0 | 7026 | 0.5463 | 0.9562 | 0.9494 | 0.9528 | 0.9429 |
| 0.0005 | 7.0 | 8197 | 0.5741 | 0.9567 | 0.9500 | 0.9533 | 0.9437 |
| 0.0004 | 8.0 | 9368 | 0.5979 | 0.9557 | 0.9494 | 0.9526 | 0.9428 |
| 0.0003 | 9.0 | 10539 | 0.6028 | 0.9558 | 0.9496 | 0.9527 | 0.9428 |
| 0.0004 | 10.0 | 11710 | 0.5936 | 0.9555 | 0.9490 | 0.9523 | 0.9426 |
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 29, 2024
- Updated
- Aug 30, 2024