laion/alfworld-swesmith-r2egym-swegym-131k-lc

<!-- 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. -->

sft__glm46-neulab-agenttuning-alfworld-sandboxes-maxeps-131k-glm46-swesmith-maxeps-131k-GLM-4-7

This model is a fine-tuned version of Qwen/Qwen3-8B on the /e/data1/datasets/playground/ot/hfhub/datasets--penfever--glm46-neulab-agenttuning-alfworld-sandboxes-maxeps-131k/snapshots/fdb0d0afe08aa3c31c7605b40c18d5e48fdc206cthinkingpreprocessed, the /e/data1/datasets/playground/ot/hfhub/datasets--penfever--glm46-swesmith-maxeps-131k/snapshots/4d4c2d4a9d21f73870ed31c7bc6028035b3b6ca7thinkingpreprocessed, the /e/data1/datasets/playground/ot/hfhub/datasets--DCAgent2--GLM-4.7-r2egymsandboxes-maxeps-131k/snapshots/167ff86e8203fa2412574480bf52623cb62320e8thinkingpreprocessed and the /e/data1/datasets/playground/ot/hfhub/datasets--DCAgent2--glm46-swegym-tasks-maxeps-131k/snapshots/bc7a253d567261d84db295a138b8af86eac6ae4cthinking_preprocessed 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: 48
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 96
• —totalevalbatch_size: 384
• —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 2.9.1+cu130
• —Datasets 4.7.0
• —Tokenizers 0.22.2