|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
base_model: distilbert-base-uncased |
|
model-index: |
|
- name: destilbert_uncased_fever_nli |
|
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. --> |
|
|
|
# destilbert_uncased_fever_nli |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on a subset of [fever_nli](https://huggingface.co/datasets/pietrolesci/nli_fever) dataset by using the first 7.5k datapoints per each label from the training split. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1829 |
|
- F1: 0.7045 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| No log | 1.0 | 352 | 0.7894 | 0.7029 | |
|
| 0.5462 | 2.0 | 704 | 0.9908 | 0.7097 | |
|
| 0.2922 | 3.0 | 1056 | 1.0831 | 0.6924 | |
|
| 0.2922 | 4.0 | 1408 | 1.2833 | 0.7044 | |
|
| 0.142 | 5.0 | 1760 | 1.4096 | 0.7008 | |
|
| 0.0695 | 6.0 | 2112 | 1.5585 | 0.7013 | |
|
| 0.0695 | 7.0 | 2464 | 1.7262 | 0.7015 | |
|
| 0.0434 | 8.0 | 2816 | 2.0138 | 0.7016 | |
|
| 0.0204 | 9.0 | 3168 | 2.0912 | 0.7012 | |
|
| 0.011 | 10.0 | 3520 | 2.1829 | 0.7045 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
