| | --- |
| | library_name: transformers |
| | language: |
| | - en |
| | license: apache-2.0 |
| | base_model: answerdotai/ModernBERT-base |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - precision |
| | - recall |
| | - f1 |
| | model-index: |
| | - name: DisambertSingleSense-base |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # DisambertSingleSense-base |
| |
|
| | This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the semcor dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 10.0010 |
| | - Precision: 0.6717 |
| | - Recall: 0.6486 |
| | - F1: 0.6599 |
| | - Matthews: 0.6479 |
| |
|
| | ## 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: 0.0001 |
| | - train_batch_size: 16 |
| | - eval_batch_size: 16 |
| | - 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: inverse_sqrt |
| | - lr_scheduler_warmup_steps: 1000 |
| | - num_epochs: 10 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Matthews | |
| | |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | | No log | 0 | 0 | 641.2748 | 0.0 | 0.0 | 0.0 | -0.0000 | |
| | | 4.9398 | 1.0 | 14014 | 7.1390 | 0.5863 | 0.5649 | 0.5754 | 0.5641 | |
| | | 1.9762 | 2.0 | 28028 | 6.1541 | 0.6409 | 0.6117 | 0.6260 | 0.6110 | |
| | | 1.1673 | 3.0 | 42042 | 6.2676 | 0.6534 | 0.6328 | 0.6429 | 0.6321 | |
| | | 0.4893 | 4.0 | 56056 | 6.9641 | 0.6609 | 0.6394 | 0.6499 | 0.6387 | |
| | | 0.2413 | 5.0 | 70070 | 7.8858 | 0.6637 | 0.6363 | 0.6497 | 0.6356 | |
| | | 0.1245 | 6.0 | 84084 | 8.9750 | 0.6662 | 0.6310 | 0.6481 | 0.6304 | |
| | | 0.0557 | 7.0 | 98098 | 9.4948 | 0.6693 | 0.6398 | 0.6542 | 0.6391 | |
| | | 0.0451 | 8.0 | 112112 | 9.7435 | 0.6682 | 0.6402 | 0.6539 | 0.6395 | |
| | | 0.0359 | 9.0 | 126126 | 9.9980 | 0.6676 | 0.6306 | 0.6486 | 0.6299 | |
| | | 0.0188 | 10.0 | 140140 | 10.0010 | 0.6717 | 0.6486 | 0.6599 | 0.6479 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 5.2.0 |
| | - Pytorch 2.6.0+cu124 |
| | - Datasets 4.5.0 |
| | - Tokenizers 0.22.2 |
| |
|
