|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: microsoft/mdeberta-v3-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: mdeberta-semeval25_narratives_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_narratives_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: 4.2105 |
|
|
- Precision Samples: 0.2832 |
|
|
- Recall Samples: 0.8213 |
|
|
- F1 Samples: 0.4012 |
|
|
- Precision Macro: 0.5829 |
|
|
- Recall Macro: 0.5521 |
|
|
- F1 Macro: 0.2820 |
|
|
- Precision Micro: 0.2788 |
|
|
- Recall Micro: 0.8273 |
|
|
- F1 Micro: 0.4170 |
|
|
- Precision Weighted: 0.3645 |
|
|
- Recall Weighted: 0.8273 |
|
|
- F1 Weighted: 0.3928 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:| |
|
|
| 5.4702 | 1.0 | 19 | 5.3912 | 0.6438 | 0.0736 | 0.0989 | 0.9687 | 0.0806 | 0.0694 | 0.3418 | 0.0971 | 0.1513 | 0.9077 | 0.0971 | 0.0642 | |
|
|
| 5.1531 | 2.0 | 38 | 5.1098 | 0.2306 | 0.5218 | 0.2960 | 0.8535 | 0.2381 | 0.1190 | 0.2310 | 0.4820 | 0.3124 | 0.6308 | 0.4820 | 0.1825 | |
|
|
| 4.9073 | 3.0 | 57 | 4.8294 | 0.3179 | 0.6244 | 0.3870 | 0.7755 | 0.3094 | 0.2019 | 0.3025 | 0.5755 | 0.3965 | 0.5337 | 0.5755 | 0.3196 | |
|
|
| 4.5067 | 4.0 | 76 | 4.5758 | 0.2886 | 0.7755 | 0.3989 | 0.6928 | 0.4553 | 0.2334 | 0.2846 | 0.7554 | 0.4134 | 0.4408 | 0.7554 | 0.3571 | |
|
|
| 4.2554 | 5.0 | 95 | 4.4310 | 0.2895 | 0.7789 | 0.4000 | 0.6933 | 0.4602 | 0.2338 | 0.2861 | 0.7626 | 0.4161 | 0.4448 | 0.7626 | 0.3613 | |
|
|
| 4.2566 | 6.0 | 114 | 4.3256 | 0.2898 | 0.7963 | 0.4034 | 0.6442 | 0.4935 | 0.2718 | 0.2868 | 0.7842 | 0.4200 | 0.4063 | 0.7842 | 0.3820 | |
|
|
| 3.9883 | 7.0 | 133 | 4.3178 | 0.2904 | 0.8055 | 0.4037 | 0.5761 | 0.5098 | 0.2688 | 0.2833 | 0.7878 | 0.4167 | 0.3586 | 0.7878 | 0.3816 | |
|
|
| 3.9572 | 8.0 | 152 | 4.2393 | 0.2798 | 0.8059 | 0.3949 | 0.5810 | 0.5428 | 0.2792 | 0.2783 | 0.8129 | 0.4147 | 0.3618 | 0.8129 | 0.3886 | |
|
|
| 4.0049 | 9.0 | 171 | 4.2153 | 0.2828 | 0.8248 | 0.4001 | 0.5814 | 0.5524 | 0.2794 | 0.2753 | 0.8309 | 0.4136 | 0.3639 | 0.8309 | 0.3915 | |
|
|
| 4.1647 | 10.0 | 190 | 4.2105 | 0.2832 | 0.8213 | 0.4012 | 0.5829 | 0.5521 | 0.2820 | 0.2788 | 0.8273 | 0.4170 | 0.3645 | 0.8273 | 0.3928 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.3.1 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.20.1 |
|
|
|
