This model is a fine-tuned version of DCAgent/g1_weighted_100k_32B_step4400 on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--g1_min_episodes_e1_weighted_top4_100k_glm47_traces/snapshots/bfc1346c9f8ed847f8803c7e766846c69f1de24a_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: 96
total_train_batch_size: 96
total_eval_batch_size: 768
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: 2.5

Training results

Framework versions

Transformers 4.57.6
Pytorch 2.9.1+cu130
Datasets 4.7.0
Tokenizers 0.22.2

DCAgent/g1_weighted_100k_32b_cont

sft_g1_weighted_100k_32b_cont__Qwen3-32B

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

DCAgent/
g1_weighted_100k_32b_cont