SoC_llama

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2722

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.3
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.3616	0.3656	100	1.3015
1.3188	0.7313	200	1.2873
1.263	1.0969	300	1.2799
1.2907	1.4625	400	1.2760
1.2168	1.8282	500	1.2722

Framework versions

• PEFT 0.11.2.dev0
• Transformers 4.43.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1