LlaMa_3.1_8B

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

• Loss: 0.5818

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 450
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7086	0.0615	100	0.6413
0.6102	0.1229	200	0.6121
0.596	0.1844	300	0.5943
0.5438	0.2459	400	0.5818

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1