llama3-fsdp-qlora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-70b on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.6181

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: 8
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.6242	0.9892	46	1.6281
1.5831	2.0	93	1.6165
1.5587	2.9677	138	1.6181

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.19.1