Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
meta-llama-Llama-3.2-3B-DottedWSD – AI Model by lopentu | AlphaNeural AI
You can deploy this model and start earning money today!
lopentu
/
meta-llama-Llama-3.2-3B-DottedWSD
like
0
peft
safetensors
llama
generated_from_trainer
meta-llama/Llama-3.2-3B
adapter
llama3.2
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
meta-llama-Llama-3.2-3B-DottedWSD
This model is a fine-tuned version of
meta-llama/Llama-3.2-3B
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.1419
Accuracy: 0.9563
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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 64
total_train_batch_size: 512
optimizer: Use 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_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.1395
0.9997
770
0.1257
0.9473
0.0797
1.9994
1540
0.1142
0.9552
0.0336
2.9991
2310
0.1419
0.9563
Framework versions
PEFT 0.13.2
Transformers 4.46.2
Pytorch 2.5.0+cu121
Datasets 3.0.1
Tokenizers 0.20.1
