Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
v1 – AI Model by aj30 | AlphaNeural AI
You can deploy this model and start earning money today!
aj30
/
v1
like
0
tensorboard
safetensors
generated_from_trainer
pubmed-dataset
meta-llama/Llama-2-7b-hf
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
v1
This model is a fine-tuned version of
meta-llama/Llama-2-7b-hf
on the pubmed-dataset dataset. It achieves the following results on the evaluation set:
Loss: 1.7454
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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
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: 0.05
num_epochs: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
1.7589
0.41
13
1.8658
1.7301
0.82
26
1.7849
1.709
1.23
39
1.7513
1.6289
1.64
52
1.7454
Framework versions
Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0
