metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: MRC_ER_mdeberta-v3-base_syl_DSC
results: []
MRC_ER_mdeberta-v3-base_syl_DSC
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: 1.9616
- Exact Match: 0.4925
- F1: 0.5963
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|
| 0.7001 | 1.0 | 3097 | 1.2355 | 0.4420 | 0.5752 |
| 0.5383 | 2.0 | 6194 | 1.4327 | 0.4784 | 0.5984 |
| 0.4088 | 3.0 | 9291 | 1.6247 | 0.4762 | 0.5947 |
| 0.282 | 4.0 | 12388 | 1.6999 | 0.4895 | 0.5986 |
| 0.2361 | 5.0 | 15485 | 1.9616 | 0.4925 | 0.5963 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1