pretrain

This model is a fine-tuned version of Qwen/Qwen2.5-32B on the openreview dataset. It achieves the following results on the evaluation set:

• Loss: 1.1076

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: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.2155	0.1604	100	1.2046
1.1392	0.3209	200	1.1238
1.1181	0.4813	300	1.1140
1.1252	0.6418	400	1.1097
1.1199	0.8022	500	1.1079
1.1104	0.9627	600	1.1075

Framework versions

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