metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: MRC_ER_mdeberta-v3-base_syl_ViWikiFC
results: []
MRC_ER_mdeberta-v3-base_syl_ViWikiFC
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5168
- Exact Match: 0.7703
- F1: 0.7925
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
|---|---|---|---|---|---|
| 0.6752 | 1.0 | 4185 | 2.1250 | 0.7421 | 0.7696 |
| 0.5728 | 2.0 | 8370 | 1.9436 | 0.7660 | 0.7865 |
| 0.4473 | 3.0 | 12555 | 2.1698 | 0.7569 | 0.7796 |
| 0.3166 | 4.0 | 16740 | 2.3835 | 0.7708 | 0.7945 |
| 0.2525 | 5.0 | 20925 | 2.5168 | 0.7703 | 0.7925 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2