Llama-3.1-8B-Instruct-EI1-120K-fix-32gpus

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

• Loss: 0.4036

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: 6e-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• total_train_batch_size: 64
• total_eval_batch_size: 256
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2924	100	0.5279
No log	0.5848	200	0.4631
No log	0.8772	300	0.4304
No log	1.1696	400	0.4153
0.4771	1.4620	500	0.4072
0.4771	1.7544	600	0.4036

Framework versions

• Transformers 4.43.4
• Pytorch 2.4.0+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1