|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: nandysoham/Dell-theme-finetuned-overfinetuned |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# nandysoham/Dell-theme-finetuned-overfinetuned |
|
|
|
This model is a fine-tuned version of [nandysoham/distilbert-base-uncased-finetuned-squad](https://huggingface.co/nandysoham/distilbert-base-uncased-finetuned-squad) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.4305 |
|
- Train End Logits Accuracy: 0.7857 |
|
- Train Start Logits Accuracy: 0.8006 |
|
- Validation Loss: 2.3316 |
|
- Validation End Logits Accuracy: 0.1647 |
|
- Validation Start Logits Accuracy: 0.2118 |
|
- Epoch: 9 |
|
|
|
## 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: |
|
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 210, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch | |
|
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:| |
|
| 1.5691 | 0.5179 | 0.5119 | 1.2093 | 0.4588 | 0.4588 | 0 | |
|
| 0.9333 | 0.6101 | 0.5833 | 1.2828 | 0.3176 | 0.3647 | 1 | |
|
| 0.7924 | 0.6042 | 0.5982 | 1.4627 | 0.2824 | 0.2824 | 2 | |
|
| 0.6858 | 0.6905 | 0.6786 | 1.5630 | 0.3059 | 0.2941 | 3 | |
|
| 0.6562 | 0.6518 | 0.6815 | 1.7647 | 0.2235 | 0.2118 | 4 | |
|
| 0.5996 | 0.7054 | 0.6994 | 2.0109 | 0.2118 | 0.2471 | 5 | |
|
| 0.5277 | 0.7440 | 0.7589 | 2.1286 | 0.1765 | 0.2000 | 6 | |
|
| 0.4810 | 0.7679 | 0.7798 | 2.2263 | 0.1529 | 0.2000 | 7 | |
|
| 0.4488 | 0.8036 | 0.7887 | 2.2999 | 0.1529 | 0.1882 | 8 | |
|
| 0.4305 | 0.7857 | 0.8006 | 2.3316 | 0.1647 | 0.2118 | 9 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- TensorFlow 2.9.2 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
