Instructions to use bimoadiparwa/roberta-mc-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bimoadiparwa/roberta-mc-2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultipleChoice tokenizer = AutoTokenizer.from_pretrained("bimoadiparwa/roberta-mc-2") model = AutoModelForMultipleChoice.from_pretrained("bimoadiparwa/roberta-mc-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from bimoadiparwa/roberta-mc-2: direct link, hf CLI and curl.
- Browser
- Download file 1.88 kB
-
https://huggingface.co/bimoadiparwa/roberta-mc-2/resolve/main/README.md
- Command line
-
hf download hf://bimoadiparwa/roberta-mc-2/README.md
-
curl -L -o README.md https://huggingface.co/bimoadiparwa/roberta-mc-2/resolve/main/README.md
1.88 kB
metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-mc-2
results: []
roberta-mc-2
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5972
- Accuracy: 0.4
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 1.6096 | 1.0 | 24 | 1.6086 | 0.3 |
| 1.614 | 2.0 | 48 | 1.6083 | 0.4 |
| 1.6032 | 3.0 | 72 | 1.6070 | 0.4 |
| 1.6185 | 4.0 | 96 | 1.6057 | 0.4 |
| 1.6106 | 5.0 | 120 | 1.6045 | 0.4 |
| 1.6093 | 6.0 | 144 | 1.6028 | 0.4 |
| 1.597 | 7.0 | 168 | 1.6010 | 0.4 |
| 1.6094 | 8.0 | 192 | 1.5994 | 0.4 |
| 1.6029 | 9.0 | 216 | 1.5977 | 0.4 |
| 1.5997 | 10.0 | 240 | 1.5972 | 0.4 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3