Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
DeepSeek-R1-Distill-Qwen-1.5B-CLM – AI Model by wh-zhu | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
wh-zhu
/
DeepSeek-R1-Distill-Qwen-1.5B-CLM
like
0
transformers
safetensors
qwen2
text-generation
llama-factory
freeze
generated_from_trainer
conversational
wh-zhu/DeepSeek-R1-Distill-Qwen-1.5B-CLM
finetune
other
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Deepseek-1.5B_pre1_sft_short_cot_lr2e-5_prompt_direct
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: 2e-05
train_batch_size: 4
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
0.2596
1.3459
500
0.2824
0.261
2.6918
1000
0.2804
Framework versions
Transformers 4.45.0
Pytorch 2.5.1+cu124
Datasets 2.21.0
Tokenizers 0.20.3
