modernbert-match-user-52992
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: 1.2588
- Accuracy: 0.7301
- F1: 0.6914
- Precision: 0.6593
- Recall: 0.7301
- F1 Class 0: 0.3478
- F1 Class 1: 0.0
- F1 Class 2: 0.16
- F1 Class 3: 0.0870
- F1 Class 4: 0.9006
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: 226
- 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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
1.0272 | 1.0 | 226 | 0.8598 | 0.7257 | 0.6487 | 0.5867 | 0.7257 | 0.2308 | 0.0 | 0.0 | 0.0 | 0.8802 |
0.7415 | 2.0 | 452 | 0.7768 | 0.7301 | 0.7034 | 0.6804 | 0.7301 | 0.3462 | 0.0 | 0.0 | 0.1395 | 0.9273 |
0.7672 | 3.0 | 678 | 0.8402 | 0.7212 | 0.6877 | 0.6731 | 0.7212 | 0.2778 | 0.0 | 0.0 | 0.16 | 0.9139 |
0.6284 | 4.0 | 904 | 1.1816 | 0.7389 | 0.7096 | 0.6877 | 0.7389 | 0.3158 | 0.1 | 0.1905 | 0.0 | 0.9281 |
0.5002 | 5.0 | 1130 | 1.2588 | 0.7301 | 0.6914 | 0.6593 | 0.7301 | 0.3478 | 0.0 | 0.16 | 0.0870 | 0.9006 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0
- Datasets 2.21.0
- Tokenizers 0.21.0
- Downloads last month
- 23
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for matiashoyl/modernbert-match-user-52992
Base model
answerdotai/ModernBERT-base