lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155

R2EGym-32B-Agent-Coder-R2egym-mid-post-step155

This model is a fine-tuned version of an internal Buffer/sample10finalstep155 checkpoint on the r2egymsfttrajectories 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: 1e-05
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 6
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 12
• —totalevalbatch_size: 48
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 2.0

Training results

Framework versions

• —Transformers 4.55.0
• —Pytorch 2.8.0+cu128
• —Datasets 3.6.0
• —Tokenizers 0.21.1