Downloads · 30 days
8
22% of all-time downloads
bert_uncased_L-6_H-512_A-8_massive
gokuls/bert_uncased_L-6_H-512_A-8_massive
bert_uncased_L-6_H-512_A-8_massive is a text classification model from gokuls. 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
37
Public
Repo size
702 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin140 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 6, 2023
- Updated
- Oct 6, 2023
- SHA
- b1af86bb
Try a prompt
Base models
Datasets
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_uncased_L-6_H-512_A-8_massive
This model is a fine-tuned version of google/bert_uncased_L-6_H-512_A-8 on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 0.5622
- Accuracy: 0.8859
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.5469 | 1.0 | 180 | 1.4077 | 0.7127 |
| 1.1262 | 2.0 | 360 | 0.8395 | 0.8195 |
| 0.6843 | 3.0 | 540 | 0.6536 | 0.8515 |
| 0.4605 | 4.0 | 720 | 0.5787 | 0.8687 |
| 0.3255 | 5.0 | 900 | 0.5451 | 0.8760 |
| 0.236 | 6.0 | 1080 | 0.5433 | 0.8790 |
| 0.1792 | 7.0 | 1260 | 0.5364 | 0.8765 |
| 0.1352 | 8.0 | 1440 | 0.5435 | 0.8829 |
| 0.1038 | 9.0 | 1620 | 0.5419 | 0.8849 |
| 0.0783 | 10.0 | 1800 | 0.5622 | 0.8819 |
| 0.0642 | 11.0 | 1980 | 0.5622 | 0.8859 |
| 0.0481 | 12.0 | 2160 | 0.5814 | 0.8819 |
| 0.0433 | 13.0 | 2340 | 0.5838 | 0.8829 |
| 0.036 | 14.0 | 2520 | 0.5810 | 0.8854 |
| 0.0331 | 15.0 | 2700 | 0.5845 | 0.8854 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Oct 6, 2023
- Updated
- Oct 6, 2023