starcoder-ft-alpaca-es-v3
This model is a fine-tuned version of bigcode/starcoder on the None dataset. It achieves the following results on the evaluation set:
- Loss: nan
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0117 | 0.27 | 200 | 0.9912 |
| 1.0515 | 0.55 | 400 | 1.0008 |
| 1.0981 | 0.82 | 600 | 1.0197 |
| 657.1807 | 1.1 | 800 | nan |
| 2927.9309 | 1.37 | 1000 | nan |
| 409.511 | 1.64 | 1200 | nan |
| 593.4789 | 1.92 | 1400 | nan |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3