qwen2.5-72b-openreviewer-mvp-1-full-review-r128

This model is a fine-tuned version of Qwen/Qwen2.5-72B on the openreview_full_review dataset. It achieves the following results on the evaluation set:

• Loss: 1.3836

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-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.532	0.5091	600	1.5193
1.4402	1.0182	1200	1.4956
1.434	1.5274	1800	1.4622
1.2638	2.0365	2400	1.4360
1.2456	2.5456	3000	1.4051
1.104	3.0547	3600	1.3918
1.0918	3.5639	4200	1.3742
1.0143	4.0730	4800	1.3840
1.0092	4.5821	5400	1.3840

Framework versions

• PEFT 0.12.0
• Transformers 4.46.1
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.20.3