Downloads · 30 days
3
11% of all-time downloads
gemma-7b_alpaca-clean_l0.0002_32-16-16
alexander-hm/gemma-7b_alpaca-clean_l0.0002_32-16-16
gemma-7b_alpaca-clean_l0.0002_32-16-16 is a machine learning model from alexander-hm. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
28
Public
Repo size
404 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors400 MB · 99%
At a glance
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Sep 20, 2024
- Updated
- Sep 26, 2024
- SHA
- 812b7c8b
Base models
Model card
From the Hugging Face model README
<!-- 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-7b_alpaca-clean_l0.0002_32-16-16
This model is a fine-tuned version of google/gemma-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3078
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: 1
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1466 | 0.0003 | 1 | 2.7341 |
| 2.374 | 0.0590 | 187 | 1.9467 |
| 1.5094 | 0.1179 | 374 | 1.9308 |
| 1.2397 | 0.1769 | 561 | 1.9313 |
| 2.2546 | 0.2359 | 748 | 2.0074 |
| 1.9981 | 0.2949 | 935 | 1.9247 |
| 1.5207 | 0.3538 | 1122 | 1.9245 |
| 1.3397 | 0.4128 | 1309 | 1.9386 |
| 2.343 | 0.4718 | 1496 | 1.9621 |
| 1.8567 | 0.5307 | 1683 | 1.9310 |
| 1.4612 | 0.5897 | 1870 | 1.9331 |
| 1.3848 | 0.6487 | 2057 | 1.9517 |
| 2.7742 | 0.7077 | 2244 | 1.9577 |
| 1.9138 | 0.7666 | 2431 | 1.9119 |
| 1.3334 | 0.8256 | 2618 | 1.9123 |
| 1.353 | 0.8846 | 2805 | 1.9439 |
| 2.6496 | 0.9436 | 2992 | 1.9501 |
| 1.0339 | 1.0025 | 3179 | 1.9334 |
| 2.7842 | 1.0615 | 3366 | 1.9900 |
| 1.4245 | 1.1205 | 3553 | 1.9951 |
| 1.2141 | 1.1794 | 3740 | 1.9619 |
| 1.0522 | 1.2384 | 3927 | 1.9756 |
| 2.3554 | 1.2974 | 4114 | 2.0143 |
| 1.2028 | 1.3564 | 4301 | 1.9821 |
| 1.1596 | 1.4153 | 4488 | 1.9642 |
| 1.3219 | 1.4743 | 4675 | 2.0006 |
| 2.3618 | 1.5333 | 4862 | 2.0003 |
| 1.4466 | 1.5922 | 5049 | 1.9769 |
| 1.1297 | 1.6512 | 5236 | 1.9820 |
| 1.3056 | 1.7102 | 5423 | 2.0430 |
| 2.2154 | 1.7692 | 5610 | 2.0169 |
| 1.2784 | 1.8281 | 5797 | 1.9743 |
| 1.1481 | 1.8871 | 5984 | 1.9651 |
| 3.0134 | 1.9461 | 6171 | 2.0564 |
| 0.7825 | 2.0050 | 6358 | 2.0322 |
| 1.0319 | 2.0640 | 6545 | 2.1380 |
| 1.711 | 2.1230 | 6732 | 2.2578 |
| 0.9755 | 2.1820 | 6919 | 2.1282 |
| 1.0064 | 2.2409 | 7106 | 2.0735 |
| 1.3375 | 2.2999 | 7293 | 2.2388 |
| 1.3544 | 2.3589 | 7480 | 2.1612 |
| 1.1275 | 2.4178 | 7667 | 2.0888 |
| 1.04 | 2.4768 | 7854 | 2.0455 |
| 1.5296 | 2.5358 | 8041 | 2.2335 |
| 1.682 | 2.5948 | 8228 | 2.1078 |
| 1.0502 | 2.6537 | 8415 | 2.0997 |
| 0.9832 | 2.7127 | 8602 | 2.0252 |
| 2.204 | 2.7717 | 8789 | 2.1709 |
| 1.4824 | 2.8307 | 8976 | 2.1082 |
| 1.1392 | 2.8896 | 9163 | 2.0663 |
| 1.052 | 2.9486 | 9350 | 2.0652 |
| 0.7344 | 3.0076 | 9537 | 2.1999 |
| 0.7813 | 3.0665 | 9724 | 2.1442 |
| 1.6681 | 3.1255 | 9911 | 2.4128 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Library
- peft
- License
- gemma
- Created
- Sep 20, 2024
- Updated
- Sep 26, 2024