This model is a fine-tuned version of Qwen/Qwen3-8B on the /e/data1/datasets/playground/ot/hf_hub/datasets--penfever--stackexchange-tezos-sandboxes__Kimi-2.5-smaxeps-32k/snapshots/33375d18f3a1d98976944789905e380fce397c46_thinking_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
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 32
gradient_accumulation_steps: 3
total_train_batch_size: 96
total_eval_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) 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 4.7.0
Tokenizers 0.22.2

laion/sft__stackexchange-tezos-sandboxes__Kimi-2-5-smaxeps-32k__Qwen3-8B

sft__stackexchange-tezos-sandboxes__Kimi-2-5-smaxeps-32k__40-0__Qwen3-8B

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

laion/
sftstackexchange-tezos-sandboxesKimi-2-5-smaxeps-32k__Qwen3-8B

sftstackexchange-tezos-sandboxesKimi-2-5-smaxeps-32k40-0Qwen3-8B