metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: starcoder-c2py-testsnippet
results: []
library_name: peft
starcoder-c2py-testsnippet
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2149
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: 7e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|
9.1209 | 0.05 | 5 | 8.5383 |
8.6626 | 0.1 | 10 | 7.4207 |
5.4255 | 0.15 | 15 | 2.9487 |
1.2743 | 0.2 | 20 | 0.6467 |
0.477 | 0.25 | 25 | 0.5785 |
0.3976 | 0.3 | 30 | 0.4535 |
0.3388 | 0.35 | 35 | 0.3448 |
0.3152 | 0.4 | 40 | 0.2857 |
0.2417 | 0.45 | 45 | 0.2603 |
0.2319 | 0.5 | 50 | 0.2460 |
0.1906 | 0.55 | 55 | 0.2362 |
0.1904 | 0.6 | 60 | 0.2296 |
0.1547 | 0.65 | 65 | 0.2246 |
0.1795 | 0.7 | 70 | 0.2214 |
0.1609 | 0.75 | 75 | 0.2193 |
0.2324 | 0.8 | 80 | 0.2174 |
0.19 | 0.85 | 85 | 0.2160 |
0.1819 | 0.9 | 90 | 0.2153 |
0.1879 | 0.95 | 95 | 0.2150 |
0.1499 | 1.0 | 100 | 0.2149 |
Framework versions
- 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