Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
opt-350m-pattern-based_finetuning_with_lora-mnli-mm-d2_fs1 – AI Model by jeanlucmarsh | AlphaNeural AI
You can deploy this model and start earning money today!
jeanlucmarsh
/
opt-350m-pattern-based_finetuning_with_lora-mnli-mm-d2_fs1
like
0
peft
tensorboard
safetensors
generated_from_trainer
glue
facebook/opt-350m
adapter
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
opt-350m-pattern-based_finetuning_with_lora-mnli-mm-d2_fs1
This model is a fine-tuned version of
facebook/opt-350m
on the glue dataset. It achieves the following results on the evaluation set:
Loss: 1.6737
Accuracy: 0.5308
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-06
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
0.3934
1.0
1
1.6780
0.5305
0.955
2.0
2
1.6763
0.5305
0.4831
3.0
3
1.6751
0.5305
0.8716
4.0
4
1.6742
0.5307
0.4978
5.0
5
1.6737
0.5308
Framework versions
PEFT 0.7.1.dev0
Transformers 4.36.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0
