|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
- NLP |
|
- Language-Model |
|
- Sentiment-Analysis |
|
- Analysis |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: my_distilbert_model |
|
results: [] |
|
datasets: |
|
- cornell-movie-review-data/rotten_tomatoes |
|
--- |
|
|
|
<!-- 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_distilbert_model |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an cornell-movie-review-data/rotten_tomatoes dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5379 |
|
- Accuracy: 0.8424 |
|
- F1: 0.8424 |
|
- Precision: 0.8424 |
|
- Recall: 0.8424 |
|
|
|
## Model description |
|
|
|
|
|
## How to use the model |
|
``` python |
|
!pip install -q transformers |
|
|
|
from huggingface_hub import notebook_login |
|
notebook_login()#after running this line enter the access token generated on your hugging face account |
|
|
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("gokarn09/my_distilbert_model") |
|
model = AutoModelForSequenceClassification.from_pretrained("gokarn09/my_distilbert_model") |
|
|
|
from transformers import pipeline |
|
text=["This is wonderful movie!", "The movie was really bad; I didn't like it."] |
|
classifier = pipeline("sentiment-analysis", model="gokarn09/my_distilbert_model") |
|
classifier(text) |
|
``` |
|
|
|
## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.4193 | 1.0 | 534 | 0.4263 | 0.8180 | 0.8162 | 0.8311 | 0.8180 | |
|
| 0.2548 | 2.0 | 1068 | 0.4289 | 0.8377 | 0.8376 | 0.8383 | 0.8377 | |
|
| 0.1582 | 3.0 | 1602 | 0.5379 | 0.8424 | 0.8424 | 0.8424 | 0.8424 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
