output

This model is a fine-tuned version of bigcode/starcoder2-3b on the fals3/methods2test_small fm+fc+c+m+f+t+tc dataset. It achieves the following results on the evaluation set:

Loss: 0.7311
Accuracy: 0.7199

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: 0.0003
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 16
total_eval_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Framework versions

PEFT 0.10.0
Transformers 4.41.0.dev0
Pytorch 2.2.1+cu118
Datasets 2.17.1
Tokenizers 0.19.1

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fals3/bigcode-starcoder2-3b-unit-test-lora

Base model

bigcode/starcoder2-3b

Adapter

(301)

this model

Dataset used to train fals3/bigcode-starcoder2-3b-unit-test-lora

Evaluation results

Accuracy on fals3/methods2test_small fm+fc+c+m+f+t+tc
self-reported

0.720