metadata
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoder
model-index:
- name: starcoder-java2py-program2
results: []
starcoder-java2py-program2
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1110
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: 2e-05
- 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: 10
- training_steps: 150
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1128 | 0.17 | 25 | 0.1122 |
| 0.1148 | 0.33 | 50 | 0.1116 |
| 0.1127 | 0.5 | 75 | 0.1113 |
| 0.1149 | 0.67 | 100 | 0.1111 |
| 0.1171 | 0.83 | 125 | 0.1110 |
| 0.1149 | 1.04 | 150 | 0.1110 |
Framework versions
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3