Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Sky-Simpo_VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5_full_normal – AI Model by secmlr | AlphaNeural AI
You can deploy this model and start earning money today!
secmlr
/
Sky-Simpo_VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5_full_normal
like
0
transformers
safetensors
qwen2
text-generation
llama-factory
full
trl
dpo
generated_from_trainer
conversational
secmlr/VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5
finetune
apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Sky-Simpo_VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5_full_normal
This model is a fine-tuned version of
secmlr/VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5
on the Sky-Simpo 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: 5e-07
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: 1.0
Training results
Framework versions
Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0
