<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
santacoder-finetuned-the-stack-bash-4
This model is a fine-tuned version of bigcode/santacoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3111
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8682 | 0.1 | 500 | 1.5485 |
| 1.4501 | 0.2 | 1000 | 1.5183 |
| 1.659 | 0.3 | 1500 | 1.4865 |
| 1.3649 | 0.4 | 2000 | 1.4528 |
| 1.4063 | 0.5 | 2500 | 1.4052 |
| 5.1385 | 0.6 | 3000 | 1.3810 |
| 1.276 | 0.7 | 3500 | 1.3462 |
| 1.5288 | 0.8 | 4000 | 1.3222 |
| 2.0152 | 0.9 | 4500 | 1.3119 |
| 1.5725 | 1.0 | 5000 | 1.3111 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
