metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: whispQuote-ChunkDQ-DistilBERT
results: []
whispQuote-ChunkDQ-DistilBERT
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2582
- Precision: 0.5816
- Recall: 0.8129
- F1: 0.6780
- Accuracy: 0.9126
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 | 164 | 0.3432 | 0.4477 | 0.5795 | 0.5052 | 0.8796 |
| No log | 2.0 | 328 | 0.3053 | 0.4308 | 0.6985 | 0.5329 | 0.8952 |
| No log | 3.0 | 492 | 0.2602 | 0.5716 | 0.7775 | 0.6588 | 0.9097 |
| 0.3826 | 4.0 | 656 | 0.2607 | 0.5664 | 0.8070 | 0.6656 | 0.9114 |
| 0.3826 | 5.0 | 820 | 0.2582 | 0.5816 | 0.8129 | 0.6780 | 0.9126 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.10.2+cu113
- Datasets 2.9.0
- Tokenizers 0.13.2