---
library_name: peft
license: gemma
base_model: google/codegemma-7b-it
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: code-bench-CodeGemma-7BIT-cg-nv9n_it_fs
  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. -->

# code-bench-CodeGemma-7BIT-cg-nv9n_it_fs

This model is a fine-tuned version of [google/codegemma-7b-it](https://huggingface.co/google/codegemma-7b-it) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0645

## 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: 3
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.7408        | 0.0530 | 50   | 0.6774          |
| 0.5161        | 0.1061 | 100  | 0.5082          |
| 0.4379        | 0.1591 | 150  | 0.3828          |
| 0.338         | 0.2121 | 200  | 0.2834          |
| 0.2648        | 0.2652 | 250  | 0.2229          |
| 0.2033        | 0.3182 | 300  | 0.1773          |
| 0.1824        | 0.3713 | 350  | 0.1469          |
| 0.1561        | 0.4243 | 400  | 0.1352          |
| 0.1482        | 0.4773 | 450  | 0.1283          |
| 0.1349        | 0.5304 | 500  | 0.1212          |
| 0.1514        | 0.5834 | 550  | 0.1157          |
| 0.1318        | 0.6364 | 600  | 0.1137          |
| 0.1327        | 0.6895 | 650  | 0.1119          |
| 0.1363        | 0.7425 | 700  | 0.1109          |
| 0.1249        | 0.7955 | 750  | 0.1075          |
| 0.1172        | 0.8486 | 800  | 0.1067          |
| 0.1187        | 0.9016 | 850  | 0.1077          |
| 0.1195        | 0.9547 | 900  | 0.1049          |
| 0.1044        | 1.0077 | 950  | 0.1022          |
| 0.1111        | 1.0607 | 1000 | 0.1025          |
| 0.1041        | 1.1138 | 1050 | 0.1019          |
| 0.1076        | 1.1668 | 1100 | 0.0989          |
| 0.1062        | 1.2198 | 1150 | 0.0991          |
| 0.1108        | 1.2729 | 1200 | 0.0968          |
| 0.1085        | 1.3259 | 1250 | 0.0961          |
| 0.0955        | 1.3789 | 1300 | 0.0949          |
| 0.0922        | 1.4320 | 1350 | 0.0943          |
| 0.1065        | 1.4850 | 1400 | 0.0935          |
| 0.1032        | 1.5381 | 1450 | 0.0920          |
| 0.094         | 1.5911 | 1500 | 0.0910          |
| 0.099         | 1.6441 | 1550 | 0.0903          |
| 0.099         | 1.6972 | 1600 | 0.0895          |
| 0.0967        | 1.7502 | 1650 | 0.0893          |
| 0.0976        | 1.8032 | 1700 | 0.0887          |
| 0.0942        | 1.8563 | 1750 | 0.0876          |
| 0.0914        | 1.9093 | 1800 | 0.0865          |
| 0.0956        | 1.9623 | 1850 | 0.0855          |
| 0.0851        | 2.0154 | 1900 | 0.0853          |
| 0.0832        | 2.0684 | 1950 | 0.0851          |
| 0.095         | 2.1215 | 2000 | 0.0854          |
| 0.0775        | 2.1745 | 2050 | 0.0840          |
| 0.0826        | 2.2275 | 2100 | 0.0828          |
| 0.0795        | 2.2806 | 2150 | 0.0831          |
| 0.0826        | 2.3336 | 2200 | 0.0828          |
| 0.0864        | 2.3866 | 2250 | 0.0810          |
| 0.0832        | 2.4397 | 2300 | 0.0802          |
| 0.0817        | 2.4927 | 2350 | 0.0796          |
| 0.0766        | 2.5457 | 2400 | 0.0789          |
| 0.0823        | 2.5988 | 2450 | 0.0783          |
| 0.0795        | 2.6518 | 2500 | 0.0780          |
| 0.0798        | 2.7049 | 2550 | 0.0771          |
| 0.0833        | 2.7579 | 2600 | 0.0770          |
| 0.0775        | 2.8109 | 2650 | 0.0760          |
| 0.0851        | 2.8640 | 2700 | 0.0755          |
| 0.0699        | 2.9170 | 2750 | 0.0746          |
| 0.0804        | 2.9700 | 2800 | 0.0743          |
| 0.0657        | 3.0231 | 2850 | 0.0746          |
| 0.0733        | 3.0761 | 2900 | 0.0735          |
| 0.064         | 3.1291 | 2950 | 0.0733          |
| 0.0662        | 3.1822 | 3000 | 0.0731          |
| 0.0643        | 3.2352 | 3050 | 0.0722          |
| 0.0625        | 3.2883 | 3100 | 0.0721          |
| 0.0621        | 3.3413 | 3150 | 0.0718          |
| 0.0664        | 3.3943 | 3200 | 0.0716          |
| 0.0696        | 3.4474 | 3250 | 0.0708          |
| 0.0626        | 3.5004 | 3300 | 0.0705          |
| 0.0653        | 3.5534 | 3350 | 0.0701          |
| 0.0564        | 3.6065 | 3400 | 0.0697          |
| 0.0623        | 3.6595 | 3450 | 0.0692          |
| 0.0613        | 3.7125 | 3500 | 0.0688          |
| 0.0607        | 3.7656 | 3550 | 0.0686          |
| 0.0582        | 3.8186 | 3600 | 0.0685          |
| 0.0555        | 3.8717 | 3650 | 0.0680          |
| 0.0549        | 3.9247 | 3700 | 0.0677          |
| 0.0618        | 3.9777 | 3750 | 0.0673          |
| 0.0549        | 4.0308 | 3800 | 0.0674          |
| 0.0514        | 4.0838 | 3850 | 0.0674          |
| 0.0492        | 4.1368 | 3900 | 0.0670          |
| 0.0576        | 4.1899 | 3950 | 0.0670          |
| 0.0563        | 4.2429 | 4000 | 0.0665          |
| 0.0512        | 4.2959 | 4050 | 0.0665          |
| 0.0557        | 4.3490 | 4100 | 0.0663          |
| 0.0691        | 4.4052 | 4150 | 0.0663          |
| 0.0662        | 4.4582 | 4200 | 0.0661          |
| 0.068         | 4.5113 | 4250 | 0.0659          |
| 0.0674        | 4.5643 | 4300 | 0.0657          |
| 0.0637        | 4.6173 | 4350 | 0.0655          |
| 0.0701        | 4.6704 | 4400 | 0.0654          |
| 0.0655        | 4.7234 | 4450 | 0.0651          |
| 0.0676        | 4.7765 | 4500 | 0.0650          |
| 0.0621        | 4.8295 | 4550 | 0.0649          |
| 0.0664        | 4.8825 | 4600 | 0.0647          |
| 0.0652        | 4.9356 | 4650 | 0.0646          |
| 0.0626        | 4.9886 | 4700 | 0.0645          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.5.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1