Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
phi-3-mini-LoRA – AI Model by HariModelMaven | AlphaNeural AI
You can deploy this model and start earning money today!
HariModelMaven
/
phi-3-mini-LoRA
like
0
peft
safetensors
trl
sft
generated_from_trainer
microsoft/Phi-3-mini-4k-instruct
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Visualize in Weights & Biases
phi-3-mini-LoRA
This model is a fine-tuned version of
microsoft/Phi-3-mini-4k-instruct
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.7447
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: 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: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
1.9803
0.4211
100
0.9842
0.8514
0.8421
200
0.8096
0.789
1.2632
300
0.7739
0.753
1.6842
400
0.7584
0.7525
2.1053
500
0.7510
0.7329
2.5263
600
0.7460
0.7356
2.9474
700
0.7447
Framework versions
PEFT 0.11.1
Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1
