studypartner/arxiv_cs_summarization_qwen2.5_7b

arxiv_cs_finetune_qwen2.5_7b_v1

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

• Loss: 0.6724

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• total_eval_batch_size: 2
• 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: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7148	0.1633	6	0.7400
0.6446	0.3265	12	0.7394
0.6581	0.4898	18	0.7079
0.6431	0.6531	24	0.6839
0.6884	0.8163	30	0.6729
0.6272	0.9796	36	0.6724

Framework versions

• PEFT 0.14.0
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1