laion/exp-psu-swesmith-1K_glm_4-7_traces_jupiter__0-005__Qwen3-8B

<!-- 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_exp-psu-swesmith-1Kglm4-7tracesjupiter0-005_Qwen3-8B

This model is a fine-tuned version of Qwen/Qwen3-8B on the /e/data1/datasets/playground/ot/hfhub/datasets--DCAgent--exp-psu-swesmith-1Kglm4.7tracesjupiter/snapshots/24c8342833108c3a15a23b64f37b83ff7e65efa4thinking_preprocessed 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: 32
• —gradientaccumulationsteps: 3
• —totaltrainbatch_size: 96
• —totalevalbatch_size: 256
• —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: 0.005
• —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