nelkh/pgd_llama3_16bits_lr0.0002_alpha32_rk4_do0.1_wd1.0e-02_1

pgd_llama3_16bits_lr0.0002_alpha32_rk4_do0.1_wd1.0e-02

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9494

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: 3
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 12
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.8705	0.9867	37	0.9906
0.9324	2.0	75	0.9176
0.9326	2.9867	112	0.9119
0.8983	4.0	150	0.9162
0.9111	4.9867	187	0.9156
0.8798	6.0	225	0.9188
0.8924	6.9867	262	0.9216
0.8557	8.0	300	0.9295
0.8666	8.9867	337	0.9393
0.8287	9.8667	370	0.9494

Framework versions

• PEFT 0.12.0
• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1