|
|
--- |
|
|
license: mit |
|
|
base_model: FacebookAI/xlm-roberta-large |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- f1 |
|
|
model-index: |
|
|
- name: clef1eng |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# clef1eng |
|
|
|
|
|
This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3082 |
|
|
- F1: 0.7683 |
|
|
|
|
|
## 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: 3e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- 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 | F1 | |
|
|
|:-------------:|:------:|:----:|:---------------:|:------:| |
|
|
| 0.417 | 0.3949 | 500 | 0.3184 | 0.7343 | |
|
|
| 0.3081 | 0.7899 | 1000 | 0.3171 | 0.7185 | |
|
|
| 0.2713 | 1.1848 | 1500 | 0.3191 | 0.7559 | |
|
|
| 0.2528 | 1.5798 | 2000 | 0.3118 | 0.7552 | |
|
|
| 0.2489 | 1.9747 | 2500 | 0.3082 | 0.7683 | |
|
|
| 0.2225 | 2.3697 | 3000 | 0.3392 | 0.7706 | |
|
|
| 0.2181 | 2.7646 | 3500 | 0.3100 | 0.7616 | |
|
|
| 0.2088 | 3.1596 | 4000 | 0.3271 | 0.7649 | |
|
|
| 0.2149 | 3.5545 | 4500 | 0.3486 | 0.7644 | |
|
|
| 0.2126 | 3.9494 | 5000 | 0.3419 | 0.7711 | |
|
|
| 0.2145 | 4.3444 | 5500 | 0.3319 | 0.7651 | |
|
|
| 0.204 | 4.7393 | 6000 | 0.3373 | 0.7723 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.40.1 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.19.1 |
|
|
|
