Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
XBRL-LoRA5050V2 – AI Model by Ben16001 | AlphaNeural AI
You can deploy this model and start earning money today!
Ben16001
/
XBRL-LoRA5050V2
like
0
peft
tensorboard
safetensors
adapter
lora
transformers
text-generation
conversational
Qwen/Qwen3-4B-Instruct-2507
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
XBRL-LoRA5050V2
This model is a fine-tuned version of
Qwen/Qwen3-4B-Instruct-2507
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.0429
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: 6.426829614559691e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
0.0645
0.4571
100
0.0597
0.0722
0.9143
200
0.0429
Framework versions
PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2
