metadata
license: mit
base_model: openai-community/gpt2-large
tags:
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: >-
RM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleTrue_extractchosenFalse
results: []
RM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleTrue_extractchosenFalse
This model is a fine-tuned version of openai-community/gpt2-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4375
- Accuracy: 0.7687
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: 1.41e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4911 | 0.17 | 250 | 0.4763 | 0.7431 |
| 0.4441 | 0.33 | 500 | 0.4547 | 0.7495 |
| 0.4323 | 0.5 | 750 | 0.4632 | 0.7601 |
| 0.4393 | 0.67 | 1000 | 0.4517 | 0.7604 |
| 0.4311 | 0.84 | 1250 | 0.4375 | 0.7687 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2