|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/mdeberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: mdeberta-semeval25_narratives09_fold2 |
|
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. --> |
|
|
|
# mdeberta-semeval25_narratives09_fold2 |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.2915 |
|
- Precision Samples: 0.3850 |
|
- Recall Samples: 0.7226 |
|
- F1 Samples: 0.4627 |
|
- Precision Macro: 0.7130 |
|
- Recall Macro: 0.4503 |
|
- F1 Macro: 0.2846 |
|
- Precision Micro: 0.3282 |
|
- Recall Micro: 0.6957 |
|
- F1 Micro: 0.4460 |
|
- Precision Weighted: 0.4983 |
|
- Recall Weighted: 0.6957 |
|
- F1 Weighted: 0.3925 |
|
|
|
## 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: 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision Samples | Recall Samples | F1 Samples | Precision Macro | Recall Macro | F1 Macro | Precision Micro | Recall Micro | F1 Micro | Precision Weighted | Recall Weighted | F1 Weighted | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:| |
|
| 5.4789 | 1.0 | 19 | 5.4030 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0476 | 0.0476 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | |
|
| 5.2627 | 2.0 | 38 | 5.1901 | 0.2839 | 0.3351 | 0.2805 | 0.9014 | 0.1655 | 0.1112 | 0.2952 | 0.2899 | 0.2925 | 0.7607 | 0.2899 | 0.1520 | |
|
| 4.6993 | 3.0 | 57 | 5.0001 | 0.3075 | 0.4274 | 0.3272 | 0.8700 | 0.2042 | 0.1344 | 0.3164 | 0.3841 | 0.3470 | 0.6843 | 0.3841 | 0.2124 | |
|
| 4.5547 | 4.0 | 76 | 4.7741 | 0.3603 | 0.5142 | 0.3949 | 0.8024 | 0.2616 | 0.1705 | 0.3290 | 0.4601 | 0.3837 | 0.5941 | 0.4601 | 0.2529 | |
|
| 4.2228 | 5.0 | 95 | 4.5899 | 0.3432 | 0.6239 | 0.4110 | 0.7733 | 0.3356 | 0.2028 | 0.3165 | 0.5688 | 0.4067 | 0.5551 | 0.5688 | 0.3071 | |
|
| 4.0369 | 6.0 | 114 | 4.4640 | 0.3575 | 0.6764 | 0.4282 | 0.7161 | 0.3926 | 0.2391 | 0.3084 | 0.6413 | 0.4165 | 0.4951 | 0.6413 | 0.3492 | |
|
| 4.0052 | 7.0 | 133 | 4.3708 | 0.3529 | 0.6907 | 0.4313 | 0.7169 | 0.4237 | 0.2521 | 0.3088 | 0.6703 | 0.4229 | 0.4941 | 0.6703 | 0.3594 | |
|
| 3.8847 | 8.0 | 152 | 4.3291 | 0.3645 | 0.7105 | 0.4445 | 0.7205 | 0.4312 | 0.2569 | 0.3170 | 0.6812 | 0.4327 | 0.5006 | 0.6812 | 0.3678 | |
|
| 3.8223 | 9.0 | 171 | 4.3064 | 0.3676 | 0.7080 | 0.4457 | 0.7196 | 0.4326 | 0.2643 | 0.3160 | 0.6812 | 0.4317 | 0.4985 | 0.6812 | 0.3716 | |
|
| 4.3457 | 10.0 | 190 | 4.2915 | 0.3850 | 0.7226 | 0.4627 | 0.7130 | 0.4503 | 0.2846 | 0.3282 | 0.6957 | 0.4460 | 0.4983 | 0.6957 | 0.3925 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.0 |
|
- Pytorch 2.3.1 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.20.1 |
|
|
