Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama3-finetuned_2024-11-09_15-48-21 – AI Model by jwoodrow22 | AlphaNeural AI
You can deploy this model and start earning money today!
jwoodrow22
/
llama3-finetuned_2024-11-09_15-48-21
like
0
peft
safetensors
trl
sft
generated_from_trainer
llama3.1
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
llama3-finetuned_2024-11-09_15-48-21
This model is a fine-tuned version of
meta-llama/Llama-3.1-8b
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.4903
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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 50
training_steps: 250
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
2.1432
0.0054
50
2.0313
1.7635
0.0108
100
1.7398
1.5704
0.0162
150
1.5788
1.4215
0.0216
200
1.5023
1.4307
0.0270
250
1.4903
Framework versions
PEFT 0.13.2
Transformers 4.45.2
Pytorch 2.5.0+cu124
Datasets 3.0.2
Tokenizers 0.20.1
