Downloads · 30 days
7
2% of all-time downloads
longformer-one-step
Theoreticallyhugo/longformer-one-step
longformer-one-step is a token classification model from Theoreticallyhugo. 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
311
Public
Parameters
148M
10.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin592 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- longformer
- Access
- Public
- Created
- Nov 27, 2023
- Updated
- Feb 6, 2024
- SHA
- a67ce5a6
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-one-step
This model is a fine-tuned version of allenai/longformer-base-4096 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5640
- Claim: {'precision': 0.5515727871250914, 'recall': 0.32811140121845084, 'f1-score': 0.4114597544338336, 'support': 2298.0}
- Majorclaim: {'precision': 0.5547752808988764, 'recall': 0.702846975088968, 'f1-score': 0.620094191522763, 'support': 1124.0}
- O: {'precision': 0.890270812437312, 'recall': 0.8831840796019901, 'f1-score': 0.8867132867132866, 'support': 5025.0}
- Premise: {'precision': 0.8300970873786407, 'recall': 0.9102287440656021, 'f1-score': 0.8683181225554106, 'support': 6951.0}
- Accuracy: 0.7994
- Macro avg: {'precision': 0.7066789919599802, 'recall': 0.7060927999937527, 'f1-score': 0.6966463388063234, 'support': 15398.0}
- Weighted avg: {'precision': 0.7880697082354996, 'recall': 0.7993895311079361, 'f1-score': 0.7880201274566476, 'support': 15398.0}
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 | Claim | Majorclaim | O | Premise | Accuracy | Macro avg | Weighted avg |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 36 | 0.7525 | {'precision': 0.41766381766381766, 'recall': 0.31897302001740646, 'f1-score': 0.36170737725141877, 'support': 2298.0} | {'precision': 0.43548387096774194, 'recall': 0.02402135231316726, 'f1-score': 0.045531197301854974, 'support': 1124.0} | {'precision': 0.7476681394207167, 'recall': 0.9092537313432836, 'f1-score': 0.8205818965517241, 'support': 5025.0} | {'precision': 0.8187416331994646, 'recall': 0.8798733995108617, 'f1-score': 0.8482074752097636, 'support': 6951.0} | 0.7433 | {'precision': 0.6048893653129352, 'recall': 0.5330303757961797, 'f1-score': 0.5190069865786904, 'support': 15398.0} | {'precision': 0.707714041883217, 'recall': 0.7432783478373814, 'f1-score': 0.7079942076273884, 'support': 15398.0} |
| No log | 2.0 | 72 | 0.6577 | {'precision': 0.4793814432989691, 'recall': 0.3237597911227154, 'f1-score': 0.38649350649350644, 'support': 2298.0} | {'precision': 0.41677503250975295, 'recall': 0.5702846975088968, 'f1-score': 0.48159278737791134, 'support': 1124.0} | {'precision': 0.7966573816155988, 'recall': 0.9106467661691542, 'f1-score': 0.849846782431052, 'support': 5025.0} | {'precision': 0.8743144424131627, 'recall': 0.8256365990504964, 'f1-score': 0.8492785793562707, 'support': 6951.0} | 0.7598 | {'precision': 0.6417820749593709, 'recall': 0.6575819634628157, 'f1-score': 0.6418029139146851, 'support': 15398.0} | {'precision': 0.7566331163186304, 'recall': 0.7598389401220937, 'f1-score': 0.7535581151939423, 'support': 15398.0} |
| No log | 3.0 | 108 | 0.5640 | {'precision': 0.5515727871250914, 'recall': 0.32811140121845084, 'f1-score': 0.4114597544338336, 'support': 2298.0} | {'precision': 0.5547752808988764, 'recall': 0.702846975088968, 'f1-score': 0.620094191522763, 'support': 1124.0} | {'precision': 0.890270812437312, 'recall': 0.8831840796019901, 'f1-score': 0.8867132867132866, 'support': 5025.0} | {'precision': 0.8300970873786407, 'recall': 0.9102287440656021, 'f1-score': 0.8683181225554106, 'support': 6951.0} | 0.7994 | {'precision': 0.7066789919599802, 'recall': 0.7060927999937527, 'f1-score': 0.6966463388063234, 'support': 15398.0} | {'precision': 0.7880697082354996, 'recall': 0.7993895311079361, 'f1-score': 0.7880201274566476, 'support': 15398.0} |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Task
- Token Classification
- Library
- transformers
- Type
- longformer
- License
- apache-2.0
- Created
- Nov 27, 2023
- Updated
- Feb 6, 2024