Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
phi1_5-sft-fast-a100_medilite_all_med_ – AI Model by olusegunola | AlphaNeural AI
You can deploy this model and start earning money today!
olusegunola
/
phi1_5-sft-fast-a100_medilite_all_med_
like
0
peft
safetensors
adapter
lora
transformers
text-generation
microsoft/phi-1_5
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Visualize in Weights & Biases
phi1_5-sft-fast-a100_medilite_all_med_
This model is a fine-tuned version of
microsoft/phi-1_5
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.6199
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 256
optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
1.6151
1.0
1427
1.6582
1.5908
2.0
2854
1.6287
1.5711
3.0
4281
1.6199
Framework versions
PEFT 0.18.1
Transformers 5.0.0.dev0
Pytorch 2.9.1+cu128
Datasets 3.2.0
Tokenizers 0.22.2
