Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
roberta-base-lora-1.18M-snli-model1 – AI Model by varun-v-rao | AlphaNeural AI
You can deploy this model and start earning money today!
varun-v-rao
/
roberta-base-lora-1.18M-snli-model1
like
0
transformers
tensorboard
safetensors
roberta
text-classification
generated_from_trainer
FacebookAI/roberta-base
finetune
mit
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
roberta-base-lora-1.18M-snli-model1
This model is a fine-tuned version of
roberta-base
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.7927
Accuracy: 0.7205
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: 256
eval_batch_size: 256
seed: 20
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.4911
1.0
2146
0.3748
0.8598
0.4514
2.0
4292
0.3540
0.8673
0.4415
3.0
6438
0.3470
0.8683
Framework versions
Transformers 4.35.2
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0
