cutelemonlili/Qwen-7B-instruct-ob-10k-30percent

ob-10k-30percent

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the ob-10k-30percent dataset. It achieves the following results on the evaluation set:

• Loss: 0.1617

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• total_eval_batch_size: 4
• 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
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.2535	0.0553	100	0.2181
0.2985	0.1106	200	0.2109
0.1578	0.1659	300	0.2008
0.1775	0.2212	400	0.2058
0.1516	0.2765	500	0.2057
0.2426	0.3319	600	0.1940
0.1668	0.3872	700	0.1940
0.1783	0.4425	800	0.1869
0.1702	0.4978	900	0.1793
0.2285	0.5531	1000	0.1762
0.1273	0.6084	1100	0.1766
0.1044	0.6637	1200	0.1706
0.1577	0.7190	1300	0.1640
0.1452	0.7743	1400	0.1632
0.1408	0.8296	1500	0.1635
0.1579	0.8850	1600	0.1623
0.1372	0.9403	1700	0.1624
0.1433	0.9956	1800	0.1622

Framework versions

• Transformers 4.46.1
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3