cpdc-qwen14-base-task1-v0-full

This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the task1_stage_0 and the task1_stage_1 datasets. It achieves the following results on the evaluation set:

• Loss: 1.2367

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.1155	1.0	140	0.9304
0.0009	2.0	280	1.1045
0.0018	3.0	420	1.0736
0.0	4.0	560	1.2187
0.0	5.0	700	1.2367

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1