|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
model-index: |
|
- name: my_awesome_model |
|
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. --> |
|
|
|
# my_awesome_model |
|
|
|
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: 0.7362 |
|
- Accuracy: {'accuracy': 0.7291666666666666} |
|
- F1: {'f1': 0.7417218543046359} |
|
- Recall: {'recall': 0.7417218543046358} |
|
- Auc: {'roc_auc': 0.7285251607289602} |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|:--------------------------:|:------------------------------:|:-------------------------------:| |
|
| No log | 0.91 | 10 | 0.5662 | {'accuracy': 0.6875} | {'f1': 0.7} | {'recall': 0.695364238410596} | {'roc_auc': 0.6870981775994585} | |
|
| No log | 1.82 | 20 | 0.5665 | {'accuracy': 0.6909722222222222} | {'f1': 0.6832740213523132} | {'recall': 0.6357615894039735} | {'roc_auc': 0.693793203461111} | |
|
| No log | 2.73 | 30 | 0.5643 | {'accuracy': 0.7256944444444444} | {'f1': 0.7127272727272727} | {'recall': 0.6490066225165563} | {'roc_auc': 0.729612800309373} | |
|
| No log | 3.64 | 40 | 0.5743 | {'accuracy': 0.7465277777777778} | {'f1': 0.750853242320819} | {'recall': 0.7284768211920529} | {'roc_auc': 0.7474500894281433} | |
|
| No log | 4.55 | 50 | 0.6057 | {'accuracy': 0.7430555555555556} | {'f1': 0.7448275862068965} | {'recall': 0.7152317880794702} | {'roc_auc': 0.7444772079083483} | |
|
| No log | 5.45 | 60 | 0.6318 | {'accuracy': 0.7291666666666666} | {'f1': 0.7382550335570469} | {'recall': 0.7284768211920529} | {'roc_auc': 0.7292019142456615} | |
|
| No log | 6.36 | 70 | 0.6664 | {'accuracy': 0.7291666666666666} | {'f1': 0.7450980392156863} | {'recall': 0.7549668874172185} | {'roc_auc': 0.7278484072122589} | |
|
| No log | 7.27 | 80 | 0.7007 | {'accuracy': 0.7222222222222222} | {'f1': 0.7241379310344827} | {'recall': 0.695364238410596} | {'roc_auc': 0.7235945279644221} | |
|
| No log | 8.18 | 90 | 0.7178 | {'accuracy': 0.7326388888888888} | {'f1': 0.7458745874587459} | {'recall': 0.7483443708609272} | {'roc_auc': 0.7318364190071059} | |
|
| No log | 9.09 | 100 | 0.7396 | {'accuracy': 0.7256944444444444} | {'f1': 0.7285223367697595} | {'recall': 0.7019867549668874} | {'roc_auc': 0.7269057862425677} | |
|
| No log | 10.0 | 110 | 0.7362 | {'accuracy': 0.7291666666666666} | {'f1': 0.7417218543046359} | {'recall': 0.7417218543046358} | {'roc_auc': 0.7285251607289602} | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
