25k_sft_5ep_021025

This model is a fine-tuned version of deepseek-ai/Deepseek-R1-Distill-Qwen-32B on the tttx/r1-trajectories-arcagi-barc, the tttx/r1-masked-arcagi-v1, the tttx/r1-barc-r1-feb-6, the tttx/r1-masked-feb-6-p2, the tttx/r1-masked-feb-6-p1, the tttx/r1-trajectories-collection-round-2, the tttx/feb7-masked-trajectories-hp12, the tttx/feb7-masked-trajectories-hp13, the tttx/regular-masked-3k-r1-020925, the tttx/regular-arcagi-3k-r1-020925, the tttx/feb10-qwen-collect-2.2k and the tttx/feb10-qwen-collect-2.7k-hp12 datasets.

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: 4
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• 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

Training results

Framework versions

• PEFT 0.13.2
• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3