---
library_name: peft
license: apache-2.0
base_model: ibm-granite/granite-3b-code-base-128k
tags:
- base_model:adapter:ibm-granite/granite-3b-code-base-128k
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: granite_3b_codebase_stage1
  results: []
---

<!-- 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. -->

# granite_3b_codebase_stage1

This model is a fine-tuned version of [ibm-granite/granite-3b-code-base-128k](https://huggingface.co/ibm-granite/granite-3b-code-base-128k) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2440

## 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: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 36
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 8
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.666         | 1.0    | 197  | 0.3711          |
| 0.3372        | 2.0    | 394  | 0.3039          |
| 0.2664        | 3.0    | 591  | 0.2736          |
| 0.2277        | 4.0    | 788  | 0.2546          |
| 0.1873        | 5.0    | 985  | 0.2456          |
| 0.1678        | 6.0    | 1182 | 0.2426          |
| 0.1512        | 7.0    | 1379 | 0.2425          |
| 0.141         | 7.9631 | 1568 | 0.2440          |


### Framework versions

- PEFT 0.17.0
- Transformers 4.50.0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4