Downloads · 30 days
11
16% of all-time downloads
longformer_result_detection
ekolasky/longformer_result_detection
longformer_result_detection is a token classification model from ekolasky. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
67
Public
Repo size
3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin592 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- longformer
- Access
- Public
- Created
- Oct 6, 2023
- Updated
- Oct 17, 2023
- SHA
- cadfa1de
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. -->
longformer_result_detection
This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1366
- Precision: 0.6230
- Recall: 0.6881
- F1: 0.6539
- Accuracy: 0.9738
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: 2
- eval_batch_size: 2
- 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 | 410 | 0.0770 | 0.5744 | 0.6056 | 0.5896 | 0.9720 |
| 0.1137 | 2.0 | 820 | 0.0612 | 0.5608 | 0.6398 | 0.5977 | 0.9723 |
| 0.056 | 3.0 | 1230 | 0.0671 | 0.6374 | 0.6861 | 0.6609 | 0.9753 |
| 0.0347 | 4.0 | 1640 | 0.0854 | 0.6026 | 0.7505 | 0.6685 | 0.9754 |
| 0.0221 | 5.0 | 2050 | 0.1062 | 0.6138 | 0.6781 | 0.6444 | 0.9732 |
| 0.0221 | 6.0 | 2460 | 0.1116 | 0.6181 | 0.7002 | 0.6566 | 0.9750 |
| 0.0119 | 7.0 | 2870 | 0.1143 | 0.6405 | 0.7565 | 0.6937 | 0.9768 |
| 0.007 | 8.0 | 3280 | 0.1303 | 0.6712 | 0.6901 | 0.6806 | 0.9747 |
| 0.0058 | 9.0 | 3690 | 0.1347 | 0.6189 | 0.6861 | 0.6508 | 0.9741 |
| 0.0036 | 10.0 | 4100 | 0.1366 | 0.6230 | 0.6881 | 0.6539 | 0.9738 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Token Classification
- Library
- transformers
- Type
- longformer
- License
- apache-2.0
- Created
- Oct 6, 2023
- Updated
- Oct 17, 2023