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

Loss: 0.1505

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
0.2457	0.0404	100	0.2433
0.1858	0.0808	200	0.2246
0.1766	0.1213	300	0.2185
0.2571	0.1617	400	0.2093
0.1863	0.2021	500	0.1982
0.2234	0.2425	600	0.2073
0.1659	0.2829	700	0.1967
0.1455	0.3234	800	0.1857
0.193	0.3638	900	0.1804
0.144	0.4042	1000	0.1794
0.1949	0.4446	1100	0.1722
0.2362	0.4850	1200	0.1727
0.2023	0.5255	1300	0.1699
0.162	0.5659	1400	0.1665
0.1616	0.6063	1500	0.1613
0.1782	0.6467	1600	0.1628
0.1397	0.6871	1700	0.1571
0.161	0.7276	1800	0.1536
0.1618	0.7680	1900	0.1541
0.1366	0.8084	2000	0.1511
0.1298	0.8488	2100	0.1517
0.1585	0.8892	2200	0.1507
0.1836	0.9297	2300	0.1507
0.124	0.9701	2400	0.1504

Framework versions

Transformers 4.46.1
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

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

officebench-10k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

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