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_model2
results: []
gpt1B_reward_model2
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: 0.0000
- 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: 1
- eval_batch_size: 1
- seed: 42
- 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 |
|---|---|---|---|---|
| 0.0 | 0.11 | 200 | 0.0124 | 0.9930 |
| 0.0002 | 0.22 | 400 | 0.0034 | 0.9965 |
| 0.0 | 0.33 | 600 | 0.0003 | 1.0 |
| 0.0 | 0.44 | 800 | 0.0003 | 1.0 |
| 0.0 | 0.55 | 1000 | 0.0003 | 1.0 |
| 0.0 | 0.65 | 1200 | 0.0004 | 1.0 |
| 0.0 | 0.76 | 1400 | 0.0000 | 1.0 |
| 0.0 | 0.87 | 1600 | 0.0000 | 1.0 |
| 0.0 | 0.98 | 1800 | 0.0000 | 1.0 |
| 0.0 | 1.09 | 2000 | 0.0000 | 1.0 |
| 0.0 | 1.2 | 2200 | 0.0000 | 1.0 |
| 0.0001 | 1.31 | 2400 | 0.0000 | 1.0 |
| 0.0 | 1.42 | 2600 | 0.0000 | 1.0 |
| 0.0 | 1.53 | 2800 | 0.0000 | 1.0 |
| 0.0 | 1.64 | 3000 | 0.0000 | 1.0 |
| 0.0 | 1.75 | 3200 | 0.0000 | 1.0 |
| 0.0 | 1.85 | 3400 | 0.0000 | 1.0 |
| 0.0 | 1.96 | 3600 | 0.0000 | 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