ft-raft-lora

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.1402

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1399
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
1.8153	0.8696	20	1.6376
1.3735	1.7391	40	1.1018
0.7809	2.6087	60	0.4950
0.3055	3.4783	80	0.2025
0.1425	4.3478	100	0.1491
0.105	5.2174	120	0.1422
0.0755	6.0870	140	0.1377
0.0602	6.9565	160	0.1402

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1