Downloads · 30 days
6
12% of all-time downloads
scenario-TCR-data-cl-massive-all_1.1
haryoaw/scenario-TCR-data-cl-massive-all_1.1
scenario-TCR-data-cl-massive-all_1.1 is a text classification model from haryoaw. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Jan 29, 2024
- Updated
- Jan 29, 2024
- SHA
- beb3c66c
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. -->
scenario-TCR-data-cl-massive-all_1.1
This model is a fine-tuned version of xlm-roberta-base on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 1.4731
- Accuracy: 0.7589
- F1: 0.7085
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.538 | 0.56 | 5000 | 1.0424 | 0.7443 | 0.6838 |
| 0.3231 | 1.11 | 10000 | 1.0765 | 0.7546 | 0.6892 |
| 0.2903 | 1.67 | 15000 | 1.0955 | 0.7515 | 0.6948 |
| 0.1815 | 2.22 | 20000 | 1.2437 | 0.7543 | 0.7015 |
| 0.1726 | 2.78 | 25000 | 1.2138 | 0.7552 | 0.7043 |
| 0.1128 | 3.33 | 30000 | 1.3161 | 0.7609 | 0.7161 |
| 0.1082 | 3.89 | 35000 | 1.3587 | 0.7586 | 0.7131 |
| 0.0635 | 4.45 | 40000 | 1.4731 | 0.7589 | 0.7085 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Jan 29, 2024
- Updated
- Jan 29, 2024