llama3-1_8b_mlfoundations-dev-stackexchange_puzzling

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

• Loss: 0.9340

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: 5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.0612	0.9908	27	1.0065
0.9481	1.9817	54	0.9614
0.8819	2.9725	81	0.9340

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.1