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_shuffleFalse_extractchosenTrue
results: []
RM-HH-AllMixNonPeft_harmless_gpt3_20000_gpt2-large_shuffleFalse_extractchosenTrue
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: 0.0405
- Accuracy: 0.9850
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 |
|---|---|---|---|---|
| 0.5457 | 0.17 | 250 | 0.0874 | 0.9654 |
| 0.5152 | 0.34 | 500 | 0.0660 | 0.9739 |
| 0.4916 | 0.51 | 750 | 0.0556 | 0.9804 |
| 0.4953 | 0.68 | 1000 | 0.0453 | 0.9827 |
| 0.4827 | 0.85 | 1250 | 0.0405 | 0.9850 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2