metadata
license: cc-by-nc-4.0
base_model: facebook/incoder-1B
tags:
- generated_from_trainer
model-index:
- name: fineTuneIncoderWithPrompt
results: []
fineTuneIncoderWithPrompt
This model is a fine-tuned version of facebook/incoder-1B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1699
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: 0.0002
- 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: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2099 | 1.0 | 500 | 0.1580 |
| 0.1301 | 2.0 | 1000 | 0.1487 |
| 0.1028 | 3.0 | 1500 | 0.1481 |
| 0.0838 | 4.0 | 2000 | 0.1547 |
| 0.069 | 5.0 | 2500 | 0.1699 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1