Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen-30b-cpt – AI Model by formalmathatepfl | AlphaNeural AI
You can deploy this model and start earning money today!
formalmathatepfl
/
Qwen-30b-cpt
like
0
transformers
safetensors
qwen3_moe
text-generation
llama-factory
full
generated_from_trainer
conversational
Qwen/Qwen3-30B-A3B-Base
finetune
other
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
cpt
This model is a fine-tuned version of
Qwen/Qwen3-30B-A3B-Base
on the lean_cpt dataset. It achieves the following results on the evaluation set:
Loss: 0.9119
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-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.03
num_epochs: 1.0
Training results
Training Loss
Epoch
Step
Validation Loss
0.9694
0.2805
100
0.9817
0.8819
0.5610
200
0.9281
0.8995
0.8415
300
0.9130
Framework versions
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2
