llama3_8b_instruct_BWRM

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2420

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: 0.0005
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.7073	0.4600	50	0.5674
0.5127	0.9201	100	0.4938
0.4164	1.3801	150	0.3664
0.3712	1.8401	200	0.3447
0.3255	2.3002	250	0.3387
0.2926	2.7602	300	0.2809
0.2725	3.2202	350	0.2721
0.254	3.6803	400	0.2562
0.2421	4.1403	450	0.2460
0.228	4.6003	500	0.2420

Framework versions

• PEFT 0.10.0
• Transformers 4.44.0
• Pytorch 2.3.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1