ideaassistant_qwen2_7b

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

• Loss: 0.4394

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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.0484	0.0955	200	1.0037
0.9828	0.1910	400	0.9110
0.8785	0.2865	600	0.8167
0.7863	0.3820	800	0.7238
0.7073	0.4776	1000	0.6407
0.6143	0.5731	1200	0.5672
0.5726	0.6686	1400	0.5096
0.5623	0.7641	1600	0.4683
0.5206	0.8596	1800	0.4465
0.5054	0.9551	2000	0.4396

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.0