Leon97ZJU/llama_query

llama

This model is a fine-tuned version of /inspire/hdd/ws-8207e9e2-e733-4eec-a475-cfa1c36480ba/embodied-multimodality/public/yli/workspace/Model/meta-llama/Llama-3.1-8B on the 2wikimultihopqa_train_clear_query, the hotpotqa_train_clear_query and the musique_train_clear_query datasets. It achieves the following results on the evaluation set:

• Loss: 0.1830

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.2035	0.2332	500	0.1948
0.2163	0.4664	1000	0.1840
0.2017	0.6996	1500	0.1708
0.1812	0.9328	2000	0.1635
0.1083	1.1660	2500	0.1655
0.1022	1.3993	3000	0.1597
0.1031	1.6325	3500	0.1551
0.0986	1.8657	4000	0.1479
0.0296	2.0989	4500	0.1816
0.0293	2.3321	5000	0.1825
0.0324	2.5653	5500	0.1819
0.0253	2.7985	6000	0.1833

Framework versions

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