sft__DCAgent2-g1_gptlong_plus_diverse_tezos_glm47_traces__Qwen-Qwen3-32B__fa2-qwen3-steps__Qwen3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 4e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 96
• total_train_batch_size: 96
• total_eval_batch_size: 768
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) 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 4.55.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.21.4