Downloads · 30 days
8
13% of all-time downloads
xlm-roberta-base_seed42_original_esp-kin-eng_train
shanhy/xlm-roberta-base_seed42_original_esp-kin-eng_train
xlm-roberta-base_seed42_original_esp-kin-eng_train is a text classification model from shanhy. 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
60
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Feb 15, 2024
- Updated
- Feb 15, 2024
- SHA
- 7e1cfb3c
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. -->
xlm-roberta-base_seed42_original_esp-kin-eng_train
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0235
- Spearman Corr: 0.7836
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
|---|---|---|---|---|
| No log | 1.81 | 200 | 0.0349 | 0.7407 |
| 0.045 | 3.62 | 400 | 0.0210 | 0.7900 |
| 0.0216 | 5.43 | 600 | 0.0227 | 0.7937 |
| 0.0164 | 7.24 | 800 | 0.0223 | 0.7939 |
| 0.0127 | 9.05 | 1000 | 0.0217 | 0.7902 |
| 0.01 | 10.86 | 1200 | 0.0189 | 0.7783 |
| 0.0084 | 12.67 | 1400 | 0.0188 | 0.7834 |
| 0.0068 | 14.48 | 1600 | 0.0228 | 0.7834 |
| 0.0057 | 16.29 | 1800 | 0.0222 | 0.7867 |
| 0.005 | 18.1 | 2000 | 0.0255 | 0.7847 |
| 0.0045 | 19.91 | 2200 | 0.0216 | 0.7842 |
| 0.0045 | 21.72 | 2400 | 0.0219 | 0.7866 |
| 0.0041 | 23.53 | 2600 | 0.0209 | 0.7850 |
| 0.0038 | 25.34 | 2800 | 0.0235 | 0.7836 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Feb 15, 2024
- Updated
- Feb 15, 2024