Downloads · 30 days
6
12% of all-time downloads
gut_1024-finetuned-lora-bert-base-t2t
LiukG/gut_1024-finetuned-lora-bert-base-t2t
gut_1024-finetuned-lora-bert-base-t2t is a text classification model from LiukG. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
51
Public
Parameters
139M
556 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors556 MB · 100%
Parameter types
How the weights are stored.
F32139M · 100%
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. -->
gut_1024-finetuned-lora-bert-base-t2t
This model is a fine-tuned version of AIRI-Institute/gena-lm-bert-base-t2t on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4700
- F1: 0.8448
- Mcc Score: 0.5728
- Accuracy: 0.7943
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Mcc Score | Accuracy |
|---|---|---|---|---|---|---|
| 0.6922 | 0.02 | 100 | 0.6644 | 0.7478 | 0.0 | 0.5971 |
| 0.6582 | 0.04 | 200 | 0.6766 | 0.4699 | 0.2578 | 0.5570 |
| 0.6578 | 0.05 | 300 | 0.5801 | 0.8210 | 0.4886 | 0.7508 |
| 0.5793 | 0.07 | 400 | 0.5814 | 0.8013 | 0.4141 | 0.7082 |
| 0.5933 | 0.09 | 500 | 0.5877 | 0.7408 | 0.4494 | 0.7183 |
| 0.5616 | 0.11 | 600 | 0.5000 | 0.8229 | 0.5282 | 0.7766 |
| 0.5168 | 0.12 | 700 | 0.5027 | 0.8347 | 0.5540 | 0.7884 |
| 0.4788 | 0.14 | 800 | 0.5284 | 0.7922 | 0.5012 | 0.7572 |
| 0.5255 | 0.16 | 900 | 0.4859 | 0.8445 | 0.5696 | 0.7901 |
| 0.5404 | 0.18 | 1000 | 0.4700 | 0.8448 | 0.5728 | 0.7943 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Mar 1, 2024
- Updated
- Mar 1, 2024