metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- indolem_sentiment
model-index:
- name: scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base
results: []
scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base
This model is a fine-tuned version of xlm-roberta-base on the indolem_sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 0.6948
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.22 | 100 | 0.4912 |
| No log | 0.44 | 200 | 0.4478 |
| No log | 0.66 | 300 | 0.3455 |
| No log | 0.88 | 400 | 0.5863 |
| 0.4809 | 1.1 | 500 | 0.3823 |
| 0.4809 | 1.32 | 600 | 0.5047 |
| 0.4809 | 1.54 | 700 | 0.6501 |
| 0.4809 | 1.76 | 800 | 0.3950 |
| 0.4809 | 1.98 | 900 | 0.6762 |
| 0.3425 | 2.2 | 1000 | 0.4929 |
| 0.3425 | 2.42 | 1100 | 0.4172 |
| 0.3425 | 2.64 | 1200 | 0.6390 |
| 0.3425 | 2.86 | 1300 | 0.6948 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3