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: 0.0078
• Accuracy: 0.9966

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3164	0.17	20	0.2708	0.9461
0.1799	0.33	40	0.1111	0.9697
0.0577	0.5	60	0.0276	0.9899
0.0064	0.66	80	0.0119	0.9933
0.0036	0.83	100	0.0099	0.9933
0.0035	0.99	120	0.0078	0.9966

Framework versions

• PEFT 0.8.2
• Transformers 4.38.1
• Pytorch 2.2.0+cu118
• Datasets 2.17.1
• Tokenizers 0.15.2