Qwen_2.5_7B_full_sft_Practice

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the mental_train_zh and the mental_train_en datasets. It achieves the following results on the evaluation set:

• Loss: 0.6514

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: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.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: 0.05
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6924	0.3876	50	0.7080
0.6314	0.7752	100	0.6708
0.4803	1.1628	150	0.6634
0.467	1.5504	200	0.6565
0.4864	1.9380	250	0.6511

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0