This model is a fine-tuned version of secmlr/DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Qwen2.5-1.5B-Instruct_sft on the simplier_reasoning_ds_clean_32k, the simplier_reasoning_ds_noisy_32k, the simplier_reasoning_ds_ossfuzz_32k, the simplier_reasoning_qwq_clean_32k, the simplier_reasoning_qwq_noisy_small_32k and the simplier_reasoning_qwq_ossfuzz_32k datasets.

Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 12
total_train_batch_size: 24
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 3.0