Instructions to use Peppizza/NLP_A2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Peppizza/NLP_A2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultipleChoice tokenizer = AutoTokenizer.from_pretrained("Peppizza/NLP_A2") model = AutoModelForMultipleChoice.from_pretrained("Peppizza/NLP_A2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Peppizza/NLP_A2: direct link, hf CLI and curl.
- Browser
- Download file 1.41 kB
-
https://huggingface.co/Peppizza/NLP_A2/resolve/main/README.md
- Command line
-
hf download hf://Peppizza/NLP_A2/README.md
-
curl -L -o README.md https://huggingface.co/Peppizza/NLP_A2/resolve/main/README.md
1.41 kB
metadata
license: cc-by-4.0
base_model: deepset/deberta-v3-large-squad2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: NLP_A2
results: []
NLP_A2
Homework model for NLP class (A2). It achieves the following results on the evaluation set:
- Loss: 0.3488
- Accuracy: 0.8840
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: 6e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9988 | 419 | 0.3791 | 0.8706 |
| 0.1279 | 1.9976 | 838 | 0.3488 | 0.8840 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1