|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: microsoft/mdeberta-v3-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: mdeberta-semeval25_fold1 |
|
|
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_fold1 |
|
|
|
|
|
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: 8.3259 |
|
|
- Precision Samples: 0.0548 |
|
|
- Recall Samples: 0.9029 |
|
|
- F1 Samples: 0.1006 |
|
|
- Precision Macro: 0.3664 |
|
|
- Recall Macro: 0.7660 |
|
|
- F1 Macro: 0.2045 |
|
|
- Precision Micro: 0.0544 |
|
|
- Recall Micro: 0.8735 |
|
|
- F1 Micro: 0.1024 |
|
|
- Precision Weighted: 0.1465 |
|
|
- Recall Weighted: 0.8735 |
|
|
- F1 Weighted: 0.1391 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:| |
|
|
| 10.7598 | 1.0 | 19 | 9.6321 | 0.0361 | 0.8335 | 0.0679 | 0.3216 | 0.7097 | 0.1401 | 0.0363 | 0.7994 | 0.0694 | 0.1978 | 0.7994 | 0.1114 | |
|
|
| 10.3024 | 2.0 | 38 | 9.2562 | 0.0422 | 0.8489 | 0.0787 | 0.4876 | 0.6843 | 0.2168 | 0.0422 | 0.8210 | 0.0803 | 0.2184 | 0.8210 | 0.1101 | |
|
|
| 9.696 | 3.0 | 57 | 9.0731 | 0.0446 | 0.8616 | 0.0828 | 0.5117 | 0.695 | 0.2535 | 0.0445 | 0.8241 | 0.0844 | 0.2189 | 0.8241 | 0.1111 | |
|
|
| 9.9846 | 4.0 | 76 | 8.8691 | 0.0462 | 0.8614 | 0.0856 | 0.4678 | 0.6926 | 0.2319 | 0.0458 | 0.8241 | 0.0868 | 0.1959 | 0.8241 | 0.1139 | |
|
|
| 9.5643 | 5.0 | 95 | 8.6872 | 0.0492 | 0.8677 | 0.0908 | 0.4610 | 0.7167 | 0.2393 | 0.0487 | 0.8395 | 0.0921 | 0.1975 | 0.8395 | 0.1216 | |
|
|
| 9.522 | 6.0 | 114 | 8.5495 | 0.0499 | 0.8787 | 0.0922 | 0.4629 | 0.7317 | 0.2542 | 0.0497 | 0.8457 | 0.0939 | 0.1827 | 0.8457 | 0.1234 | |
|
|
| 9.1263 | 7.0 | 133 | 8.4783 | 0.0518 | 0.8849 | 0.0954 | 0.4306 | 0.7354 | 0.2449 | 0.0513 | 0.8488 | 0.0968 | 0.1533 | 0.8488 | 0.1307 | |
|
|
| 9.2682 | 8.0 | 152 | 8.3858 | 0.0536 | 0.8928 | 0.0985 | 0.4086 | 0.7496 | 0.2234 | 0.0532 | 0.8642 | 0.1001 | 0.1551 | 0.8642 | 0.1342 | |
|
|
| 9.1804 | 9.0 | 171 | 8.3447 | 0.0536 | 0.8928 | 0.0985 | 0.3996 | 0.7503 | 0.2145 | 0.0531 | 0.8642 | 0.1001 | 0.1581 | 0.8642 | 0.1365 | |
|
|
| 8.8361 | 10.0 | 190 | 8.3259 | 0.0548 | 0.9029 | 0.1006 | 0.3664 | 0.7660 | 0.2045 | 0.0544 | 0.8735 | 0.1024 | 0.1465 | 0.8735 | 0.1391 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.3.1 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.20.1 |
|
|
|
