|
--- |
|
license: apache-2.0 |
|
base_model: casual/nlp_til2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: nlp_til2 |
|
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. --> |
|
|
|
# nlp_til2 |
|
|
|
This model is a fine-tuned version of [casual/nlp_til2](https://huggingface.co/casual/nlp_til2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0041 |
|
- Precision: 0.9920 |
|
- Recall: 0.9923 |
|
- F1: 0.9921 |
|
- Accuracy: 0.9987 |
|
|
|
## 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: 18 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 219 | 0.0286 | 0.9350 | 0.9281 | 0.9316 | 0.9896 | |
|
| No log | 2.0 | 438 | 0.0277 | 0.9439 | 0.9235 | 0.9336 | 0.9899 | |
|
| 0.0365 | 3.0 | 657 | 0.0296 | 0.9127 | 0.9300 | 0.9213 | 0.9890 | |
|
| 0.0365 | 4.0 | 876 | 0.0267 | 0.9232 | 0.9404 | 0.9317 | 0.9900 | |
|
| 0.0332 | 5.0 | 1095 | 0.0205 | 0.9451 | 0.9599 | 0.9524 | 0.9929 | |
|
| 0.0332 | 6.0 | 1314 | 0.0165 | 0.9725 | 0.9542 | 0.9633 | 0.9942 | |
|
| 0.0293 | 7.0 | 1533 | 0.0145 | 0.9729 | 0.9579 | 0.9653 | 0.9946 | |
|
| 0.0293 | 8.0 | 1752 | 0.0156 | 0.9577 | 0.9658 | 0.9617 | 0.9944 | |
|
| 0.0293 | 9.0 | 1971 | 0.0111 | 0.9756 | 0.9737 | 0.9746 | 0.9961 | |
|
| 0.0237 | 10.0 | 2190 | 0.0091 | 0.9773 | 0.9803 | 0.9788 | 0.9968 | |
|
| 0.0237 | 11.0 | 2409 | 0.0088 | 0.9750 | 0.9803 | 0.9777 | 0.9968 | |
|
| 0.0199 | 12.0 | 2628 | 0.0068 | 0.9888 | 0.9848 | 0.9868 | 0.9978 | |
|
| 0.0199 | 13.0 | 2847 | 0.0070 | 0.9835 | 0.9847 | 0.9841 | 0.9977 | |
|
| 0.0201 | 14.0 | 3066 | 0.0074 | 0.9834 | 0.9861 | 0.9848 | 0.9976 | |
|
| 0.0201 | 15.0 | 3285 | 0.0051 | 0.9869 | 0.9889 | 0.9879 | 0.9983 | |
|
| 0.0257 | 16.0 | 3504 | 0.0040 | 0.9921 | 0.9913 | 0.9917 | 0.9987 | |
|
| 0.0257 | 17.0 | 3723 | 0.0045 | 0.9911 | 0.9922 | 0.9916 | 0.9987 | |
|
| 0.0257 | 18.0 | 3942 | 0.0041 | 0.9920 | 0.9923 | 0.9921 | 0.9987 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
