DCAgent/g1_diverse_tezos_100k_32b

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

sftg1diversetezos100k32b_Qwen3-32B

This model is a fine-tuned version of Qwen/Qwen3-32B on the /e/scratch/jureap59/raoof1/sftdata/hfhub/datasets--DCAgent--g1diversetezostop4100kglm47traces/snapshots/0a6a1ada0b105252bbf82f1434ca3c858f57bbb7thinkingpreprocessed 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
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 96
• —totaltrainbatch_size: 96
• —totalevalbatch_size: 768
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 5.0

Training results

Framework versions

• —Transformers 4.57.6
• —Pytorch 2.9.1+cu130
• —Datasets 4.7.0
• —Tokenizers 0.22.2