modernbert-match-user-52922
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: 1.4871
- Accuracy: 0.4617
- F1: 0.4291
- Precision: 0.4374
- Recall: 0.4617
- F1 Class 0: 0.3771
- F1 Class 1: 0.1212
- F1 Class 2: 0.2917
- F1 Class 3: 0.1159
- F1 Class 4: 0.6667
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: 392
- 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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
1.4394 | 1.0 | 392 | 1.5130 | 0.4541 | 0.2836 | 0.2062 | 0.4541 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6246 |
1.3892 | 2.0 | 784 | 1.3713 | 0.4694 | 0.3492 | 0.3787 | 0.4694 | 0.0882 | 0.2162 | 0.0357 | 0.0645 | 0.6489 |
1.3124 | 3.0 | 1176 | 1.3548 | 0.4541 | 0.3599 | 0.3945 | 0.4541 | 0.0606 | 0.2020 | 0.2133 | 0.0351 | 0.6448 |
1.201 | 4.0 | 1568 | 1.3669 | 0.4592 | 0.4283 | 0.4188 | 0.4592 | 0.2264 | 0.2162 | 0.2330 | 0.2174 | 0.6748 |
1.0585 | 5.0 | 1960 | 1.4871 | 0.4617 | 0.4291 | 0.4374 | 0.4617 | 0.3771 | 0.1212 | 0.2917 | 0.1159 | 0.6667 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0
- Datasets 2.21.0
- Tokenizers 0.21.0
- Downloads last month
- 16
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for matiashoyl/modernbert-match-user-52922
Base model
answerdotai/ModernBERT-base