metadata
base_model: MoritzLaurer/deberta-v3-large-zeroshot-v2.0
library_name: peft
license: mit
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-arcchallenge
results: []
datasets:
- allenai/ai2_arc
fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-arcchallenge
This model is a fine-tuned version of MoritzLaurer/deberta-v3-large-zeroshot-v2.0 on ARC-Challenge dataset. It achieves the following results on the evaluation set:
- Loss: 1.6476
- Accuracy: 0.6087
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: 1.5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 70 | 0.9709 | 0.6421 |
| No log | 2.0 | 140 | 1.0093 | 0.6321 |
| No log | 3.0 | 210 | 1.2280 | 0.6455 |
| No log | 4.0 | 280 | 1.4439 | 0.6355 |
| No log | 5.0 | 350 | 1.6110 | 0.6120 |
| No log | 6.0 | 420 | 1.6476 | 0.6087 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1