Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama3.2-3b-aqag-finetuned-kaggle-20K-save-by-epochs – AI Model by Shahdooz25 | AlphaNeural AI
You can deploy this model and start earning money today!
Shahdooz25
/
llama3.2-3b-aqag-finetuned-kaggle-20K-save-by-epochs
like
0
peft
tensorboard
safetensors
llama
trl
sft
generated_from_trainer
generator
meta-llama/Llama-3.2-3B
adapter
llama3.2
4-bit
bitsandbytes
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
llama3.2-3b-aqag-finetuned-kaggle-20K-save-by-epochs
This model is a fine-tuned version of
meta-llama/Llama-3.2-3B
on the generator dataset. It achieves the following results on the evaluation set:
Loss: 1.2456
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: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
1.3027
0.3325
280
1.3024
1.2652
0.6651
560
1.2789
1.2842
0.9976
840
1.2732
1.2359
1.3302
1120
1.2577
1.2284
1.6627
1400
1.2475
1.2152
1.9952
1680
1.2456
Framework versions
PEFT 0.13.2
Transformers 4.45.2
Pytorch 2.10.0+cu128
Datasets 4.8.3
Tokenizers 0.20.3
