This model is a fine-tuned version of secmlr/DS-Clean_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5 on the ruizhe_simplier_reasoning_ds_clean_32k, the ruizhe_simplier_reasoning_ds_noisy_32k, the ruizhe_simplier_reasoning_qwq_clean_32k and the ruizhe_simplier_reasoning_qwq_noisy_small_32k 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: 1e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 12
total_train_batch_size: 48
total_eval_batch_size: 32
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

Training results

Framework versions

Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0

secmlr/ruizhe_simplier_dsNsy32kCln32k_QwQNsy32kCln32k_DSCln_QWQCln_Qwen7B_summarized_sft

ruizhe_simplier_dsNsy32kCln32k_QwQNsy32kCln32k_DSCln_QWQCln_Qwen7B_summarized_sft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

secmlr/
ruizhe_simplier_dsNsy32kCln32k_QwQNsy32kCln32k_DSCln_QWQCln_Qwen7B_summarized_sft