metadata
license: openrail
tags:
- generated_from_trainer
model-index:
- name: santacoder-finetuned-the-stack-bash-shell
results: []
santacoder-finetuned-the-stack-bash-shell
This model is a fine-tuned version of bigcode/santacoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2272
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6101 | 0.05 | 500 | 1.5078 |
| 1.6156 | 0.1 | 1000 | 1.4687 |
| 1.4916 | 0.15 | 1500 | 1.4728 |
| 1.4027 | 0.2 | 2000 | 1.4237 |
| 1.499 | 0.25 | 2500 | 1.4067 |
| 1.4378 | 0.3 | 3000 | 1.3838 |
| 1.3698 | 0.35 | 3500 | 1.3767 |
| 1.3021 | 0.4 | 4000 | 1.3562 |
| 4.0521 | 0.45 | 4500 | 1.3433 |
| 0.9722 | 0.5 | 5000 | 1.3461 |
| 1.3836 | 0.55 | 5500 | 1.2955 |
| 1.3727 | 0.6 | 6000 | 1.2809 |
| 1.3332 | 0.65 | 6500 | 1.2665 |
| 1.2232 | 0.7 | 7000 | 1.2573 |
| 1.2373 | 0.75 | 7500 | 1.2463 |
| 1.3759 | 0.8 | 8000 | 1.2391 |
| 1.3021 | 0.85 | 8500 | 1.2325 |
| 1.369 | 0.9 | 9000 | 1.2292 |
| 1.4911 | 0.95 | 9500 | 1.2275 |
| 1.1677 | 1.0 | 10000 | 1.2272 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2