Instructions to use Ariffiq99/Stacked_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ariffiq99/Stacked_model with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultipleChoice tokenizer = AutoTokenizer.from_pretrained("Ariffiq99/Stacked_model") model = AutoModelForMultipleChoice.from_pretrained("Ariffiq99/Stacked_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Ariffiq99/Stacked_model: direct link, hf CLI and curl.
- Browser
- Download file 1.63 kB
-
https://huggingface.co/Ariffiq99/Stacked_model/resolve/main/README.md
- Command line
-
hf download hf://Ariffiq99/Stacked_model/README.md
-
curl -L -o README.md https://huggingface.co/Ariffiq99/Stacked_model/resolve/main/README.md
1.63 kB
metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Stacked_model_20%
results: []
Stacked_model_20%
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8958
- F1: 0.6875
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: 1e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 316 | 0.9812 | 0.6313 |
| 1.0979 | 2.0 | 632 | 0.9134 | 0.6660 |
| 1.0979 | 3.0 | 948 | 0.8894 | 0.6840 |
| 0.8229 | 4.0 | 1264 | 0.8829 | 0.6831 |
| 0.7182 | 5.0 | 1580 | 0.8958 | 0.6875 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1