Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
starcoder-finetuned-code2code – AI Model by jlpan | AlphaNeural AI
You can deploy this model and start earning money today!
jlpan
/
starcoder-finetuned-code2code
like
0
generated_from_trainer
bigcode/starcoder
finetune
bigcode-openrail-m
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
starcoder-finetuned-code2code
This model is a fine-tuned version of
bigcode/starcoder
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.3667
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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 600
Training results
Training Loss
Epoch
Step
Validation Loss
0.7191
0.17
100
0.4499
0.4506
0.33
200
0.3985
0.3988
0.5
300
0.3807
0.3684
0.67
400
0.3709
0.3499
0.83
500
0.3670
0.3438
1.0
600
0.3667
Framework versions
Transformers 4.32.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3
