Downloads · 30 days
9
20% of all-time downloads
bert-base-uncased_Synonym-wordnet
avinasht/bert-base-uncased_Synonym-wordnet
bert-base-uncased_Synonym-wordnet is a text classification model from avinasht. Use it when you need a label for a piece of text. 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
45
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Feb 21, 2024
- Updated
- Feb 21, 2024
- SHA
- 42e453f3
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. -->
bert-base-uncased_Synonym-wordnet
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2882
- Accuracy: 0.9189
- F1: 0.9188
- Precision: 0.9198
- Recall: 0.9189
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.9015 | 1.0 | 91 | 0.8202 | 0.6864 | 0.6880 | 0.6985 | 0.6864 |
| 0.4453 | 2.0 | 182 | 0.3882 | 0.8596 | 0.8603 | 0.8639 | 0.8596 |
| 0.2615 | 3.0 | 273 | 0.3010 | 0.8892 | 0.8886 | 0.8919 | 0.8892 |
| 0.1806 | 4.0 | 364 | 0.3460 | 0.8783 | 0.8784 | 0.8820 | 0.8783 |
| 0.1357 | 5.0 | 455 | 0.2867 | 0.9173 | 0.9170 | 0.9177 | 0.9173 |
| 0.0545 | 6.0 | 546 | 0.2882 | 0.9189 | 0.9188 | 0.9198 | 0.9189 |
| 0.0536 | 7.0 | 637 | 0.3650 | 0.9002 | 0.9006 | 0.9035 | 0.9002 |
| 0.1393 | 8.0 | 728 | 0.3927 | 0.9064 | 0.9058 | 0.9095 | 0.9064 |
| 0.0796 | 9.0 | 819 | 0.4371 | 0.8986 | 0.8980 | 0.8996 | 0.8986 |
| 0.0546 | 10.0 | 910 | 0.3807 | 0.9095 | 0.9090 | 0.9100 | 0.9095 |
| 0.0869 | 11.0 | 1001 | 0.4038 | 0.8970 | 0.8959 | 0.8981 | 0.8970 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Feb 21, 2024
- Updated
- Feb 21, 2024