Openthoughts-3-QwQ-32b-annotated-16k_qwen2.5-1.5B_16k

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the open-thoughts/OpenThoughts3-1.2M dataset (which is created using QwQ 32B with 16k output length).

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: 0.00015
• weight_decay: 0.0
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 256
• total_train_batch_size: 256
• total_eval_batch_size: 2048
• optimizer: Use adamw_torch_fused with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1