metadata
library_name: transformers
license: apache-2.0
base_model: EuroBERT/EuroBERT-210m
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: eurobert_Eau
results: []
eurobert_Eau
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: 0.1286
- Accuracy: 0.9508
- F1: 0.9491
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8035 | 1.0 | 67 | 0.4268 | 0.8809 | 0.8836 |
| 0.3476 | 2.0 | 134 | 0.2320 | 0.9168 | 0.9174 |
| 0.263 | 3.0 | 201 | 0.2839 | 0.9031 | 0.9010 |
| 0.2119 | 4.0 | 268 | 0.1522 | 0.9385 | 0.9393 |
| 0.191 | 5.0 | 335 | 0.1765 | 0.9314 | 0.9296 |
| 0.1797 | 6.0 | 402 | 0.1228 | 0.9480 | 0.9474 |
| 0.1639 | 7.0 | 469 | 0.1065 | 0.9485 | 0.9500 |
| 0.1422 | 8.0 | 536 | 0.1347 | 0.9428 | 0.9423 |
| 0.1237 | 9.0 | 603 | 0.1047 | 0.9504 | 0.9510 |
| 0.1119 | 10.0 | 670 | 0.1286 | 0.9508 | 0.9491 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0