QwQ-32B_enable-liger-kernel_False_OpenThoughts3_10k

This model is a fine-tuned version of /p/data1/mmlaion/dcft/hub/models--Qwen--QwQ-32B/snapshots/976055f8c83f394f35dbd3ab09a285a984907bd0 on the /p/data1/mmlaion/dcft/hub/mlfoundations-dev___open_thoughts3_10k/default/0.0.0/470c9d2d08f0e75e97f9791a716ad6d0e2e07087 dataset.

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: 4e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 128
• total_train_batch_size: 128
• total_eval_batch_size: 1024
• 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

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.0a0+b465a5843b.nv24.09
• Datasets 3.6.0
• Tokenizers 0.20.3