Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
opt-350m-finetuned-v2-seinfeld – AI Model by sdeg | AlphaNeural AI
You can deploy this model and start earning money today!
sdeg
/
opt-350m-finetuned-v2-seinfeld
like
0
transformers
pytorch
tensorboard
opt
text-generation
generated_from_trainer
other
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
opt-350m-finetuned-v2-seinfeld
This model is a fine-tuned version of
facebook/opt-350m
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 2.6803
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: 0.0005
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
2.9453
1.0
25
2.8188
2.7838
2.0
50
2.7364
2.616
3.0
75
2.7089
Framework versions
Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.0
Tokenizers 0.13.2
