Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Llama2-7B-lora-r-32-generic-step-150-lr-1e-5-labels_40.0 – AI Model by Siqi-Hu | AlphaNeural AI
You can deploy this model and start earning money today!
Siqi-Hu
/
Llama2-7B-lora-r-32-generic-step-150-lr-1e-5-labels_40.0
like
0
peft
tensorboard
safetensors
generated_from_trainer
meta-llama/Llama-2-7b-hf
adapter
llama2
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Llama2-7B-lora-r-32-generic-step-150-lr-1e-5-labels_40.0
This model is a fine-tuned version of
meta-llama/Llama-2-7b-hf
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 3.9580
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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
training_steps: 150
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
5.4596
0.3653
20
5.4980
4.8001
0.7306
40
4.8078
4.3599
1.0959
60
4.3370
4.0715
1.4612
80
4.1228
3.8997
1.8265
100
4.0174
3.9087
2.1918
120
3.9713
3.8547
2.5571
140
3.9580
Framework versions
PEFT 0.15.2
Transformers 4.45.2
Pytorch 2.5.0+cu121
Datasets 3.2.0
Tokenizers 0.20.3
