Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Uno-Orchestra-7B-SFT – AI Model by tinaxie | AlphaNeural AI
You can deploy this model and start earning money today!
tinaxie
/
Uno-Orchestra-7B-SFT
like
0
transformers
safetensors
qwen2
text-generation
llama-factory
full
generated_from_trainer
conversational
Qwen/Qwen2.5-7B-Instruct
finetune
other
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
router_qwen25_7b_sft_clean
This model is a fine-tuned version of
/home/xieht/data/models/Qwen/Qwen2.5-7B-Instruct-real
on the router_sft_clean dataset. It achieves the following results on the evaluation set:
Loss: 0.2659
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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 128
total_eval_batch_size: 4
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: 100
num_epochs: 2.0
Training results
Training Loss
Epoch
Step
Validation Loss
0.3832
0.4323
50
0.3854
0.3099
0.8646
100
0.2908
0.2488
1.2940
150
0.2764
0.2433
1.7263
200
0.2676
Framework versions
Transformers 5.2.0
Pytorch 2.11.0+cu130
Datasets 4.0.0
Tokenizers 0.22.2
