This model is a fine-tuned version of Qwen/Qwen3-32B on the /e/data1/datasets/playground/ot/hf_hub/datasets--penfever--glm-4.6-r2egym-32ep-32k/snapshots/1b98f51e65d71b6dc9702529884355b93b8b8685_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--penfever--GLM-4.6-nl2bash-verified-32eps-32k/snapshots/61e17458d760f1419c4447abbab4fc93118563dd_thinking_preprocessed, the /e/data1/datasets/playground/ot/hf_hub/datasets--penfever--GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k/snapshots/1c13e68d92fc88775a6a593c5ca93a4a4bae0a38_thinking_preprocessed and the /e/data1/datasets/playground/ot/hf_hub/datasets--penfever--GLM-4.6-inferredbugs-32eps-65k/snapshots/60d83f48605156a6b9182f9b54c6da2d4dffc061_thinking_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
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 48
gradient_accumulation_steps: 2
total_train_batch_size: 96
total_eval_batch_size: 384
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7.0

Training results

Framework versions

Transformers 4.57.6
Pytorch 2.9.1+cu130
Datasets 4.4.1
Tokenizers 0.22.2

laion/sft_r2egym-nl2bash-stackoverflow-inferredbugs-32B_Qwen3-32B

sft_r2egym-nl2bash-stackoverflow-inferredbugs-32B_Qwen3-32B

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

laion/
sft_r2egym-nl2bash-stackoverflow-inferredbugs-32B_Qwen3-32B