|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: token_fine_tunned_flipkart |
|
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. --> |
|
|
|
# token_fine_tunned_flipkart |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0992 |
|
- Precision: 0.9526 |
|
- Recall: 0.9669 |
|
- F1: 0.9597 |
|
- Accuracy: 0.9730 |
|
|
|
## 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: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 135 | 0.5967 | 0.7227 | 0.7830 | 0.7516 | 0.7932 | |
|
| No log | 2.0 | 270 | 0.3673 | 0.8105 | 0.8623 | 0.8356 | 0.8747 | |
|
| No log | 3.0 | 405 | 0.2679 | 0.8676 | 0.8854 | 0.8764 | 0.9094 | |
|
| 0.6219 | 4.0 | 540 | 0.1972 | 0.8955 | 0.9217 | 0.9084 | 0.9355 | |
|
| 0.6219 | 5.0 | 675 | 0.1500 | 0.9229 | 0.9374 | 0.9301 | 0.9525 | |
|
| 0.6219 | 6.0 | 810 | 0.1240 | 0.9341 | 0.9509 | 0.9424 | 0.9609 | |
|
| 0.6219 | 7.0 | 945 | 0.1041 | 0.9516 | 0.9650 | 0.9582 | 0.9720 | |
|
| 0.2085 | 8.0 | 1080 | 0.0992 | 0.9526 | 0.9669 | 0.9597 | 0.9730 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.19.2 |
|
- Pytorch 1.11.0+cu102 |
|
- Datasets 2.2.2 |
|
- Tokenizers 0.12.1 |
|
|
