Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
opt-125m-lora-finetuned-mnli – AI Model by velaa | AlphaNeural AI
You can deploy this model and start earning money today!
velaa
/
opt-125m-lora-finetuned-mnli
like
0
tensorboard
safetensors
generated_from_trainer
glue
facebook/opt-125m
finetune
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
opt-125m-lora-finetuned-mnli
This model is a fine-tuned version of
facebook/opt-125m
on the glue dataset. It achieves the following results on the evaluation set:
Loss: 1.1926
Accuracy: 0.3313
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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
1.1562
1.0
1
1.1948
0.3302
1.1512
2.0
2
1.1938
0.3309
1.131
3.0
3
1.1931
0.3311
1.15
4.0
4
1.1928
0.3312
1.0987
5.0
5
1.1926
0.3313
Framework versions
Transformers 4.36.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0
