metadata
library_name: transformers
license: mit
base_model: KoNqUeRoR3891/HW2-supervised
tags:
- trl
- reward-trainer
- generated_from_trainer
datasets:
- piqa
metrics:
- accuracy
model-index:
- name: HW2-reward
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: piqa
type: piqa
config: plain_text
split: train
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.640818858560794
HW2-reward
This model is a fine-tuned version of KoNqUeRoR3891/HW2-supervised on the piqa dataset. It achieves the following results on the evaluation set:
- Loss: 0.7024
- Accuracy: 0.6408
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6793 | 1.0 | 3626 | 0.6733 | 0.5782 |
0.6767 | 2.0 | 7252 | 0.6590 | 0.6210 |
0.5686 | 3.0 | 10878 | 0.7024 | 0.6408 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1