lemonhat/Qwen2.5-Coder-7B-Instruct-2and3_apps_30k_v6

2and3_apps_30k_v6

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the 2and3_apps_30k_v6 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1605

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: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
0.1745	0.1025	100	0.1826
0.1915	0.2049	200	0.1744
0.1889	0.3074	300	0.1699
0.203	0.4098	400	0.1674
0.1834	0.5123	500	0.1656
0.1807	0.6148	600	0.1633
0.1853	0.7172	700	0.1625
0.173	0.8197	800	0.1614
0.1793	0.9221	900	0.1606

Framework versions

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