Downloads · 30 days
9
17% of all-time downloads
scibert_all_deep
jialinselenasong/scibert_all_deep
scibert_all_deep is a token classification model from jialinselenasong. 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
52
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
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- May 9, 2024
- Updated
- May 9, 2024
- SHA
- 0ca64422
Try a prompt
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. -->
scibert_all_deep
This model is a fine-tuned version of allenai/scibert_scivocab_cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8270
- Precision: 0.6648
- Recall: 0.7172
- F1: 0.6900
- Accuracy: 0.8207
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 363 | 0.5559 | 0.6191 | 0.6867 | 0.6511 | 0.8131 |
| 0.6741 | 2.0 | 726 | 0.5344 | 0.6271 | 0.7101 | 0.6660 | 0.8203 |
| 0.3917 | 3.0 | 1089 | 0.5548 | 0.6558 | 0.7064 | 0.6801 | 0.8205 |
| 0.3917 | 4.0 | 1452 | 0.5835 | 0.6717 | 0.7110 | 0.6908 | 0.8246 |
| 0.271 | 5.0 | 1815 | 0.6643 | 0.6524 | 0.7255 | 0.6870 | 0.8196 |
| 0.188 | 6.0 | 2178 | 0.7021 | 0.6724 | 0.7067 | 0.6892 | 0.8222 |
| 0.1437 | 7.0 | 2541 | 0.7594 | 0.6555 | 0.7180 | 0.6853 | 0.8191 |
| 0.1437 | 8.0 | 2904 | 0.7916 | 0.6664 | 0.7109 | 0.6879 | 0.8194 |
| 0.114 | 9.0 | 3267 | 0.8123 | 0.6582 | 0.7225 | 0.6888 | 0.8203 |
| 0.0943 | 10.0 | 3630 | 0.8270 | 0.6648 | 0.7172 | 0.6900 | 0.8207 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- May 9, 2024
- Updated
- May 9, 2024