metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: token-classification-llmlingua2-xlm-roberta-41k_remove_stop_word_1_epoch
results: []
token-classification-llmlingua2-xlm-roberta-41k_remove_stop_word_1_epoch
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2371
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2156 | 0.1 | 50 | 0.3222 |
| 0.143 | 0.19 | 100 | 0.2533 |
| 0.131 | 0.29 | 150 | 0.2444 |
| 0.1297 | 0.39 | 200 | 0.2433 |
| 0.1282 | 0.48 | 250 | 0.2413 |
| 0.1272 | 0.58 | 300 | 0.2436 |
| 0.125 | 0.68 | 350 | 0.2382 |
| 0.1274 | 0.77 | 400 | 0.2383 |
| 0.1263 | 0.87 | 450 | 0.2376 |
| 0.1232 | 0.97 | 500 | 0.2371 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2