|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
base_model: distilbert-base-cased |
|
model-index: |
|
- name: whispQuote-ChunkedDQ |
|
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. --> |
|
|
|
# whispQuote-ChunkedDQ |
|
|
|
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2317 |
|
- Precision: 0.6456 |
|
- Recall: 0.8030 |
|
- F1: 0.7157 |
|
- Accuracy: 0.9241 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 162 | 0.3050 | 0.5572 | 0.6886 | 0.6159 | 0.8903 | |
|
| No log | 2.0 | 324 | 0.2382 | 0.6363 | 0.7659 | 0.6951 | 0.9187 | |
|
| No log | 3.0 | 486 | 0.2350 | 0.6420 | 0.7927 | 0.7094 | 0.9220 | |
|
| 0.3239 | 4.0 | 648 | 0.2303 | 0.6486 | 0.8012 | 0.7169 | 0.9228 | |
|
| 0.3239 | 5.0 | 810 | 0.2317 | 0.6456 | 0.8030 | 0.7157 | 0.9241 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.10.2+cu113 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
