|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: microsoft/mdeberta-v3-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: mdeberta-semeval25_narratives_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_narratives_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: 4.2885 |
|
|
- Precision Samples: 0.3350 |
|
|
- Recall Samples: 0.7536 |
|
|
- F1 Samples: 0.4333 |
|
|
- Precision Macro: 0.6879 |
|
|
- Recall Macro: 0.4863 |
|
|
- F1 Macro: 0.2811 |
|
|
- Precision Micro: 0.3050 |
|
|
- Recall Micro: 0.7283 |
|
|
- F1 Micro: 0.4299 |
|
|
- Precision Weighted: 0.4670 |
|
|
- Recall Weighted: 0.7283 |
|
|
- F1 Weighted: 0.3780 |
|
|
|
|
|
## 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 | 0.3379 | 0.1101 | 0.1439 | 0.9654 | 0.0927 | 0.0678 | 0.2727 | 0.1304 | 0.1765 | 0.8999 | 0.1304 | 0.0583 | |
|
|
| 5.2624 | 2.0 | 38 | 5.1901 | 0.2247 | 0.5133 | 0.2910 | 0.8525 | 0.2352 | 0.1174 | 0.225 | 0.4565 | 0.3014 | 0.6426 | 0.4565 | 0.1720 | |
|
|
| 4.6987 | 3.0 | 57 | 4.9982 | 0.2978 | 0.6055 | 0.3677 | 0.8057 | 0.2903 | 0.1710 | 0.2788 | 0.5181 | 0.3625 | 0.5895 | 0.5181 | 0.2450 | |
|
|
| 4.55 | 4.0 | 76 | 4.7729 | 0.2885 | 0.6683 | 0.3752 | 0.7661 | 0.3656 | 0.1967 | 0.2783 | 0.6232 | 0.3848 | 0.5364 | 0.6232 | 0.2905 | |
|
|
| 4.2177 | 5.0 | 95 | 4.5872 | 0.2936 | 0.7137 | 0.3912 | 0.7287 | 0.3965 | 0.2139 | 0.2907 | 0.6594 | 0.4035 | 0.4982 | 0.6594 | 0.3199 | |
|
|
| 4.032 | 6.0 | 114 | 4.4578 | 0.3081 | 0.7260 | 0.4059 | 0.7040 | 0.4315 | 0.2385 | 0.2881 | 0.6920 | 0.4068 | 0.4759 | 0.6920 | 0.3423 | |
|
|
| 4.0007 | 7.0 | 133 | 4.3653 | 0.3220 | 0.7352 | 0.4198 | 0.6836 | 0.4669 | 0.2688 | 0.2964 | 0.7174 | 0.4195 | 0.4618 | 0.7174 | 0.3671 | |
|
|
| 3.8824 | 8.0 | 152 | 4.3266 | 0.3438 | 0.7605 | 0.4395 | 0.6859 | 0.4861 | 0.2784 | 0.3042 | 0.7319 | 0.4298 | 0.4668 | 0.7319 | 0.3779 | |
|
|
| 3.819 | 9.0 | 171 | 4.3024 | 0.3296 | 0.7444 | 0.4272 | 0.6865 | 0.4734 | 0.2753 | 0.3015 | 0.7210 | 0.4252 | 0.4659 | 0.7210 | 0.3735 | |
|
|
| 4.3455 | 10.0 | 190 | 4.2885 | 0.3350 | 0.7536 | 0.4333 | 0.6879 | 0.4863 | 0.2811 | 0.3050 | 0.7283 | 0.4299 | 0.4670 | 0.7283 | 0.3780 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.3.1 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.20.1 |
|
|
|
