|
--- |
|
base_model: unsloth/gemma-2-9b |
|
library_name: peft |
|
license: gemma |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: gemma-2-9b_metamath_ortho |
|
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. --> |
|
|
|
# gemma-2-9b_metamath_ortho |
|
|
|
This model is a fine-tuned version of [unsloth/gemma-2-9b](https://huggingface.co./unsloth/gemma-2-9b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 10.4991 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7559 | 0.0211 | 13 | 11.2124 | |
|
| 11.6216 | 0.0421 | 26 | 11.5534 | |
|
| 11.3932 | 0.0632 | 39 | 11.2944 | |
|
| 10.8497 | 0.0843 | 52 | 10.5202 | |
|
| 10.6949 | 0.1053 | 65 | 10.3737 | |
|
| 10.205 | 0.1264 | 78 | 10.8305 | |
|
| 10.3395 | 0.1474 | 91 | 11.1255 | |
|
| 10.8575 | 0.1685 | 104 | 10.1467 | |
|
| 10.5782 | 0.1896 | 117 | 10.6096 | |
|
| 10.5443 | 0.2106 | 130 | 10.3814 | |
|
| 10.4871 | 0.2317 | 143 | 10.6978 | |
|
| 10.4177 | 0.2528 | 156 | 10.8357 | |
|
| 9.3249 | 0.2738 | 169 | 9.7925 | |
|
| 11.959 | 0.2949 | 182 | 12.0069 | |
|
| 12.0051 | 0.3159 | 195 | 11.9632 | |
|
| 11.9939 | 0.3370 | 208 | 11.9428 | |
|
| 11.711 | 0.3581 | 221 | 11.8586 | |
|
| 11.7235 | 0.3791 | 234 | 11.4550 | |
|
| 11.4001 | 0.4002 | 247 | 11.5482 | |
|
| 11.3359 | 0.4213 | 260 | 11.1959 | |
|
| 11.5279 | 0.4423 | 273 | 11.5632 | |
|
| 11.3903 | 0.4634 | 286 | 11.0193 | |
|
| 11.2189 | 0.4845 | 299 | 11.1413 | |
|
| 11.0779 | 0.5055 | 312 | 10.9722 | |
|
| 11.0063 | 0.5266 | 325 | 10.8490 | |
|
| 11.1246 | 0.5476 | 338 | 11.1407 | |
|
| 10.9858 | 0.5687 | 351 | 10.7436 | |
|
| 10.6825 | 0.5898 | 364 | 11.2291 | |
|
| 11.3333 | 0.6108 | 377 | 11.0195 | |
|
| 10.9347 | 0.6319 | 390 | 10.9265 | |
|
| 10.7369 | 0.6530 | 403 | 10.7926 | |
|
| 10.7869 | 0.6740 | 416 | 10.7711 | |
|
| 10.7802 | 0.6951 | 429 | 10.6187 | |
|
| 10.8631 | 0.7162 | 442 | 10.8749 | |
|
| 10.6492 | 0.7372 | 455 | 10.6884 | |
|
| 10.7395 | 0.7583 | 468 | 10.6685 | |
|
| 10.7239 | 0.7793 | 481 | 10.5783 | |
|
| 10.5349 | 0.8004 | 494 | 10.4897 | |
|
| 10.3873 | 0.8215 | 507 | 10.6675 | |
|
| 10.4529 | 0.8425 | 520 | 10.5227 | |
|
| 10.4378 | 0.8636 | 533 | 10.4906 | |
|
| 10.5446 | 0.8847 | 546 | 10.5181 | |
|
| 10.469 | 0.9057 | 559 | 10.4954 | |
|
| 10.4688 | 0.9268 | 572 | 10.4928 | |
|
| 10.4527 | 0.9478 | 585 | 10.4564 | |
|
| 10.4343 | 0.9689 | 598 | 10.4873 | |
|
| 10.4796 | 0.9900 | 611 | 10.4991 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
