|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: xlmr-finetuned |
|
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. --> |
|
|
|
# xlmr-finetuned |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3897 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 3.1718 | 0.29 | 500 | 2.5733 | |
|
| 2.8822 | 0.59 | 1000 | 2.3739 | |
|
| 2.7361 | 0.88 | 1500 | 2.3563 | |
|
| 2.6077 | 1.18 | 2000 | 2.2466 | |
|
| 2.4731 | 1.47 | 2500 | 2.2027 | |
|
| 2.4545 | 1.76 | 3000 | 2.2104 | |
|
| 2.467 | 2.06 | 3500 | 2.0885 | |
|
| 2.3209 | 2.35 | 4000 | 2.0476 | |
|
| 2.2937 | 2.64 | 4500 | 1.9431 | |
|
| 2.2624 | 2.94 | 5000 | 1.9157 | |
|
| 2.1502 | 3.23 | 5500 | 1.8811 | |
|
| 2.1445 | 3.53 | 6000 | 1.8488 | |
|
| 2.1308 | 3.82 | 6500 | 1.8074 | |
|
| 2.0752 | 4.11 | 7000 | 1.8089 | |
|
| 2.032 | 4.41 | 7500 | 1.7853 | |
|
| 2.0253 | 4.7 | 8000 | 1.7723 | |
|
| 1.9904 | 4.99 | 8500 | 1.6976 | |
|
| 1.9348 | 5.29 | 9000 | 1.6399 | |
|
| 1.9116 | 5.58 | 9500 | 1.6159 | |
|
| 1.9105 | 5.88 | 10000 | 1.5930 | |
|
| 1.8649 | 6.17 | 10500 | 1.5590 | |
|
| 1.8108 | 6.46 | 11000 | 1.5662 | |
|
| 1.8084 | 6.76 | 11500 | 1.5504 | |
|
| 1.7835 | 7.05 | 12000 | 1.5933 | |
|
| 1.7324 | 7.34 | 12500 | 1.5500 | |
|
| 1.7358 | 7.64 | 13000 | 1.4570 | |
|
| 1.726 | 7.93 | 13500 | 1.4775 | |
|
| 1.6477 | 8.23 | 14000 | 1.4382 | |
|
| 1.6768 | 8.52 | 14500 | 1.4717 | |
|
| 1.6073 | 8.81 | 15000 | 1.4162 | |
|
| 1.6516 | 9.11 | 15500 | 1.4516 | |
|
| 1.6084 | 9.4 | 16000 | 1.4209 | |
|
| 1.6013 | 9.69 | 16500 | 1.3874 | |
|
| 1.608 | 9.99 | 17000 | 1.3897 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
