modernbert-match-user-52311
This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9250
- Accuracy: 0.7704
- F1: 0.7375
- Precision: 0.7301
- Recall: 0.7704
- F1 Class 0: 0.6154
- F1 Class 1: 0.1429
- F1 Class 2: 0.4348
- F1 Class 3: 0.2
- F1 Class 4: 0.9036
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: 4
- eval_batch_size: 4
- 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: cosine_with_restarts
- lr_scheduler_warmup_steps: 135
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | F1 Class 0 | F1 Class 1 | F1 Class 2 | F1 Class 3 | F1 Class 4 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
1.085 | 1.0 | 135 | 0.9149 | 0.6889 | 0.6239 | 0.5797 | 0.6889 | 0.0 | 0.0 | 0.3429 | 0.1818 | 0.8643 |
0.8932 | 2.0 | 270 | 0.9514 | 0.7185 | 0.6617 | 0.6198 | 0.7185 | 0.4118 | 0.0 | 0.2222 | 0.0 | 0.8844 |
0.6533 | 3.0 | 405 | 1.1794 | 0.7259 | 0.6466 | 0.6471 | 0.7259 | 0.3636 | 0.0 | 0.4 | 0.0 | 0.8465 |
0.6124 | 4.0 | 540 | 0.9250 | 0.7704 | 0.7375 | 0.7301 | 0.7704 | 0.6154 | 0.1429 | 0.4348 | 0.2 | 0.9036 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0
- Datasets 2.21.0
- Tokenizers 0.21.0
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for matiashoyl/modernbert-match-user-52311
Base model
answerdotai/ModernBERT-base