Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen2.5-32b-ins-lora-50-toy-pure – AI Model by metacog0 | AlphaNeural AI
You can deploy this model and start earning money today!
metacog0
/
qwen2.5-32b-ins-lora-50-toy-pure
like
0
peft
safetensors
llama-factory
lora
generated_from_trainer
Qwen/Qwen2.5-32B-Instruct
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
qwen2.5-32b-ins-lora-50-toy-pure
This model is a fine-tuned version of
Qwen/Qwen2.5-32B-Instruct
on the pure_toy_2k dataset. It achieves the following results on the evaluation set:
Loss: 0.0113
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: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 8
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_ratio: 0.1
num_epochs: 4.0
Training results
Training Loss
Epoch
Step
Validation Loss
No log
1.0
36
0.0745
No log
2.0
72
0.0245
0.0711
3.0
108
0.0123
0.0711
4.0
144
0.0113
Framework versions
PEFT 0.15.2
Transformers 4.55.0
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1
