metadata
library_name: transformers
license: apache-2.0
base_model: EuroBERT/EuroBERT-210m
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: eurobert210m_Sentiment_v2
results: []
eurobert210m_Sentiment_v2
This model is a fine-tuned version of EuroBERT/EuroBERT-210m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0163
- Accuracy: 0.9964
- F1: 0.9964
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3156 | 1.0 | 407 | 0.1217 | 0.9585 | 0.9586 |
| 0.1475 | 2.0 | 814 | 0.0722 | 0.9774 | 0.9775 |
| 0.0939 | 3.0 | 1221 | 0.0426 | 0.9869 | 0.9870 |
| 0.0739 | 4.0 | 1628 | 0.0341 | 0.9899 | 0.9899 |
| 0.0592 | 5.0 | 2035 | 0.0280 | 0.9912 | 0.9912 |
| 0.0389 | 6.0 | 2442 | 0.0225 | 0.9936 | 0.9936 |
| 0.0333 | 7.0 | 2849 | 0.0141 | 0.9955 | 0.9955 |
| 0.0335 | 8.0 | 3256 | 0.0322 | 0.9930 | 0.9930 |
| 0.0257 | 9.0 | 3663 | 0.0139 | 0.9957 | 0.9957 |
| 0.0219 | 10.0 | 4070 | 0.0098 | 0.9969 | 0.9969 |
| 0.0192 | 11.0 | 4477 | 0.0127 | 0.9959 | 0.9959 |
| 0.0253 | 12.0 | 4884 | 0.0284 | 0.9926 | 0.9926 |
| 0.0211 | 13.0 | 5291 | 0.0163 | 0.9964 | 0.9964 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1