Downloads · 30 days
11
24% of all-time downloads
bert_uncased_L-2_H-512_A-8_mrpc
gokulsrinivasagan/bert_uncased_L-2_H-512_A-8_mrpc
bert_uncased_L-2_H-512_A-8_mrpc is a text classification model from gokulsrinivasagan. 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
46
Public
Parameters
22.5M
270 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors89.8 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 4, 2024
- Updated
- Dec 4, 2024
- SHA
- 619d920a
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-2_H-512_A-8_mrpc
This model is a fine-tuned version of google/bert_uncased_L-2_H-512_A-8 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5133
- Accuracy: 0.7525
- F1: 0.8319
- Combined Score: 0.7922
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6181 | 1.0 | 15 | 0.5675 | 0.7034 | 0.8158 | 0.7596 |
| 0.5593 | 2.0 | 30 | 0.5351 | 0.7279 | 0.8257 | 0.7768 |
| 0.5034 | 3.0 | 45 | 0.5392 | 0.75 | 0.8416 | 0.7958 |
| 0.4395 | 4.0 | 60 | 0.5133 | 0.7525 | 0.8319 | 0.7922 |
| 0.3721 | 5.0 | 75 | 0.5677 | 0.7598 | 0.8393 | 0.7996 |
| 0.3062 | 6.0 | 90 | 0.6190 | 0.7353 | 0.8188 | 0.7770 |
| 0.2538 | 7.0 | 105 | 0.6957 | 0.7377 | 0.8243 | 0.7810 |
| 0.191 | 8.0 | 120 | 0.7498 | 0.7230 | 0.8120 | 0.7675 |
| 0.1475 | 9.0 | 135 | 0.8235 | 0.7451 | 0.8278 | 0.7865 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Dec 4, 2024
- Updated
- Dec 4, 2024