PEFT Unit Test Generation Experiments
Collection
40 items • Updated
output
This model is a fine-tuned version of bigcode/starcoder2-3b on the andstor/methods2test_small fm+fc+c+m+f+t+tc dataset. It achieves the following results on the evaluation set:
- Loss: 0.7535
- Accuracy: 0.7196
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
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for andstor/bigcode-starcoder2-3b-unit-test-ia3
Base model
bigcode/starcoder2-3bDataset used to train andstor/bigcode-starcoder2-3b-unit-test-ia3
Collection including andstor/bigcode-starcoder2-3b-unit-test-ia3
Evaluation results
- Accuracy on andstor/methods2test_small fm+fc+c+m+f+t+tcself-reported0.720
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-3b") model = PeftModel.from_pretrained(base_model, "andstor/bigcode-starcoder2-3b-unit-test-ia3")