Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
gpt-neo-1.3B_peft_ft – AI Model by ishikaibm | AlphaNeural AI
You can deploy this model and start earning money today!
ishikaibm
/
gpt-neo-1.3B_peft_ft
like
0
peft
safetensors
generated_from_trainer
google-bert/bert-base-uncased
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gpt-neo-1.3B_peft_ft
This model is a fine-tuned version of
google-bert/bert-base-uncased
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 7.5942
Accuracy: 9630.1814
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: 0.005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
No log
1.0
1
9.3535
12436.1706
No log
2.0
2
8.6990
13080.6173
No log
3.0
3
8.1906
9042.9082
No log
4.0
4
7.7776
9702.7354
No log
5.0
5
7.5942
9630.1814
Framework versions
PEFT 0.11.1
Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1
