llama2-7b-int4-dolly-15k-english-unsloth-w-packing-qk-modules

This model is a fine-tuned version of unsloth/llama-2-7b on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.2366

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: 6
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.3265	0.64	100	1.2591
1.2244	1.27	200	1.2438
1.2123	1.91	300	1.2381
1.2025	2.55	400	1.2366

Framework versions

• PEFT 0.7.2.dev0
• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0