llama_8b_lima_44

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

• Loss: 0.9029

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: 5.5e-06
• train_batch_size: 3
• eval_batch_size: 2
• seed: 66
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 6
• total_train_batch_size: 36
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: polynomial
• lr_scheduler_warmup_steps: 50
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.0313	0.0974	80	0.9290
0.985	0.1948	160	0.9194
1.091	0.2923	240	0.9109
0.9087	0.3897	320	0.9030
1.0107	0.4871	400	0.8975
0.9108	0.5845	480	0.8940
1.1531	0.6820	560	0.9039
1.2698	0.7794	640	0.9069
1.1988	0.8768	720	0.9063
1.1649	0.9742	800	0.9046

Framework versions

• Transformers 4.46.1
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.3