Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
sanskrit-poetry-qwen3-5-27b-trainability-pilot-masked3-lora – AI Model by ascerfcefc | AlphaNeural AI
You can deploy this model and start earning money today!
ascerfcefc
/
sanskrit-poetry-qwen3-5-27b-trainability-pilot-masked3-lora
like
0
peft
safetensors
adapter
lora
transformers
text-generation
conversational
Qwen/Qwen3.5-27B
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
sanskrit-poetry-qwen3-5-27b-trainability-pilot-masked3-lora
This model is a fine-tuned version of
Qwen/Qwen3.5-27B
on the None dataset. It achieves the following results on the evaluation set:
Loss: 2.2213
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: 8e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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
training_steps: 30
Training results
Training Loss
Epoch
Step
Validation Loss
3.1858
0.2768
10
2.9771
2.4749
0.5536
20
2.3284
2.2396
0.8304
30
2.2213
Framework versions
PEFT 0.19.1
Transformers 5.6.2
Pytorch 2.8.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2
