llama3.1_8b_bwgenerator

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

• Loss: 0.0819

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: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.295	0.3287	20	0.3356
0.264	0.6574	40	0.2187
0.1974	0.9861	60	0.1787
0.1648	1.3148	80	0.1482
0.1311	1.6436	100	0.1131
0.1006	1.9723	120	0.0901
0.0864	2.3010	140	0.0844
0.0836	2.6297	160	0.0823
0.0824	2.9584	180	0.0819

Framework versions

• PEFT 0.10.0
• Transformers 4.44.0
• Pytorch 2.3.0+cu121
• Datasets 2.14.7
• Tokenizers 0.19.1