metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: starcoder-c2py-testprogram
results: []
library_name: peft
starcoder-c2py-testprogram
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1295
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1742 | 0.05 | 5 | 0.1665 |
| 0.1587 | 0.1 | 10 | 0.1619 |
| 0.1361 | 0.15 | 15 | 0.1568 |
| 0.1516 | 0.2 | 20 | 0.1486 |
| 0.141 | 0.25 | 25 | 0.1429 |
| 0.1292 | 0.3 | 30 | 0.1405 |
| 0.1461 | 0.35 | 35 | 0.1374 |
| 0.09 | 0.4 | 40 | 0.1351 |
| 0.1149 | 0.45 | 45 | 0.1332 |
| 0.1296 | 0.5 | 50 | 0.1325 |
| 0.1069 | 1.05 | 55 | 0.1334 |
| 0.1046 | 1.1 | 60 | 0.1320 |
| 0.0969 | 1.15 | 65 | 0.1308 |
| 0.1141 | 1.2 | 70 | 0.1304 |
| 0.1182 | 1.25 | 75 | 0.1300 |
| 0.1112 | 1.3 | 80 | 0.1297 |
| 0.1278 | 1.35 | 85 | 0.1295 |
| 0.0794 | 1.4 | 90 | 0.1295 |
| 0.1067 | 1.45 | 95 | 0.1295 |
| 0.1164 | 1.5 | 100 | 0.1295 |
Framework versions
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- 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