metadata
library_name: peft
license: apache-2.0
base_model: unsloth/codegemma-2b
tags:
- axolotl
- generated_from_trainer
model-index:
- name: a7c9fd50-c061-4752-b720-b2d3d69762bc
results: []
a7c9fd50-c061-4752-b720-b2d3d69762bc
This model is a fine-tuned version of unsloth/codegemma-2b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5859
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: 0.000207
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0000 | 1 | 2.9066 |
| 1.6797 | 0.0016 | 50 | 1.8520 |
| 1.6838 | 0.0032 | 100 | 1.8346 |
| 1.8328 | 0.0049 | 150 | 1.7967 |
| 1.6822 | 0.0065 | 200 | 1.7772 |
| 1.7255 | 0.0081 | 250 | 1.7434 |
| 1.5466 | 0.0097 | 300 | 1.6769 |
| 1.5499 | 0.0113 | 350 | 1.6311 |
| 1.549 | 0.0130 | 400 | 1.6061 |
| 1.5332 | 0.0146 | 450 | 1.5877 |
| 1.4883 | 0.0162 | 500 | 1.5859 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1