Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3-8b-gsm8k-P1-multi-n500-seed42-lora-all – AI Model by xummer | AlphaNeural AI
You can deploy this model and start earning money today!
xummer
/
qwen3-8b-gsm8k-P1-multi-n500-seed42-lora-all
like
0
peft
safetensors
adapter
llama-factory
lora
transformers
text-generation
conversational
Qwen/Qwen3-8B
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gsm8k_P1_multi_n500_seed42
This model is a fine-tuned version of
Qwen/Qwen3-8B
on the gsm8k_multi_n500_train dataset. It achieves the following results on the evaluation set:
Loss: 0.4027
Accuracy: 0.8867
Mcq Accuracy: 0.4111
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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
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: 0.1
num_epochs: 3.0
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
Mcq Accuracy
0.3750
0.7111
200
0.4143
0.8843
0.4111
0.3533
1.4196
400
0.4063
0.8856
0.4022
0.3148
2.128
600
0.4037
0.8860
0.4067
0.3150
2.8391
800
0.4028
0.8868
0.4111
Framework versions
PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2
