Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
final-llama-3-all-fixed – AI Model by tanjumajerin | AlphaNeural AI
You can deploy this model and start earning money today!
tanjumajerin
/
final-llama-3-all-fixed
like
0
peft
safetensors
generated_from_trainer
meta-llama/Meta-Llama-3-8B
adapter
llama3
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
final-llama-3-all-fixed
This model is a fine-tuned version of
meta-llama/Meta-Llama-3-8B
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.1460
Accuracy: 0.5755
F1: 0.6085
Precision: 0.5563
Recall: 0.6716
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
F1
Precision
Recall
0.6866
0.9999
5167
1.1525
0.5706
0.5994
0.5532
0.6540
0.5318
1.9997
10334
1.1460
0.5755
0.6085
0.5563
0.6716
Framework versions
PEFT 0.10.0
Transformers 4.40.0
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.19.1
