lemonhat/Qwen2.5-Coder-7B-Instruct-t1_25k_v2_tag5

t1_25k_v2_tag5

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the t1_25k_v2_tag5 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2605

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: 5e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• 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
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.3427	0.0817	100	0.3218
0.2658	0.1634	200	0.3040
0.2831	0.2451	300	0.2921
0.2759	0.3268	400	0.2846
0.3056	0.4085	500	0.2798
0.2839	0.4902	600	0.2763
0.3051	0.5719	700	0.2703
0.3155	0.6536	800	0.2688
0.2373	0.7353	900	0.2634
0.2561	0.8170	1000	0.2620
0.2546	0.8987	1100	0.2609
0.2504	0.9804	1200	0.2606

Framework versions

• Transformers 4.46.1
• Pytorch 2.6.0+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3