Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen7b-llama-sft-p1-d0-apec – AI Model by Justin-ChenZhen | AlphaNeural AI
You can deploy this model and start earning money today!
Justin-ChenZhen
/
qwen7b-llama-sft-p1-d0-apec
like
0
peft
safetensors
llama-factory
lora
generated_from_trainer
Qwen/Qwen2.5-7B-Instruct
adapter
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
qwen7b-llama-sft-p1-d0-apec
This model is a fine-tuned version of
/home/cz/ragen/models/Qwen/Qwen2.5-7B-Instruct
on the ragen_qa dataset. It achieves the following results on the evaluation set:
Loss: 0.3453
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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 5
gradient_accumulation_steps: 32
total_train_batch_size: 160
total_eval_batch_size: 5
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4.0
Training results
Training Loss
Epoch
Step
Validation Loss
0.3755
2.2302
20
0.3571
Framework versions
PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1
