metadata
license: apache-2.0
library_name: peft
tags:
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
base_model: AI-Sweden-Models/gpt-sw3-1.3b
model-index:
- name: gpt1B_reward_model
results: []
gpt1B_reward_model
This model is a fine-tuned version of AI-Sweden-Models/gpt-sw3-1.3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0017
- Accuracy: 1.0
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1303 | 0.41 | 50 | 0.1400 | 0.9697 |
| 0.0606 | 0.83 | 100 | 0.0171 | 0.9865 |
| 0.0005 | 1.24 | 150 | 0.0036 | 1.0 |
| 0.0 | 1.65 | 200 | 0.0017 | 1.0 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2