laion/r2egym-nl2bash-stack-bugsseq-fixthink-again

<!-- 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. -->

r2egym-nl2bash-stack-bugsseq-fixthink-again

This model is a fine-tuned version of Qwen/Qwen3-8B on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--glm-4.6-r2egym-32ep-32k/snapshots/1b98f51e65d71b6dc9702529884355b93b8b8685thinkingpreprocessed, the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-nl2bash-verified-32eps-32k/snapshots/61e17458d760f1419c4447abbab4fc93118563ddthinkingpreprocessed, the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k/snapshots/1c13e68d92fc88775a6a593c5ca93a4a4bae0a38thinkingpreprocessed and the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-inferredbugs-32eps-65k/snapshots/60d83f48605156a6b9182f9b54c6da2d4dffc061thinkingpreprocessed 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: 4e-05
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —totalevalbatch_size: 64
• —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: 7.0

Training results

Framework versions

• —Transformers 4.57.6
• —Pytorch 2.9.0+cu128
• —Datasets 4.4.1
• —Tokenizers 0.22.2