zhangchenxu/Qwen2.5-3B-Instruct-t2_25k_v2_tag4_processed

t2_25k_v2_tag4_processed

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the t2_25k_v2_tag4_processed dataset. It achieves the following results on the evaluation set:

• Loss: 0.3884

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
0.3013	0.2410	100	0.4413
0.3485	0.4819	200	0.4096
0.307	0.7229	300	0.3916
0.2568	0.9639	400	0.3886

Framework versions

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