Downloads · 30 days
4
15% of all-time downloads
llama-7b_alpaca-clean_l0.0002_64
alexander-hm/llama-7b_alpaca-clean_l0.0002_64
llama-7b_alpaca-clean_l0.0002_64 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 other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Repo size
845 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors844 MB · 100%
At a glance
- Library
- peft
- License
- other
- Access
- Public
- Created
- Sep 24, 2024
- Updated
- Sep 29, 2024
- SHA
- 0524a65a
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. -->
llama-7b_alpaca-clean_l0.0002_64
This model is a fine-tuned version of huggyllama/llama-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5531
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: 0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1814 | 0.0003 | 1 | 2.3690 |
| 1.9908 | 0.0590 | 187 | 1.6049 |
| 1.3656 | 0.1179 | 374 | 1.5985 |
| 1.1021 | 0.1769 | 561 | 1.5950 |
| 1.8912 | 0.2359 | 748 | 1.5595 |
| 1.6795 | 0.2949 | 935 | 1.5425 |
| 1.2666 | 0.3538 | 1122 | 1.5377 |
| 1.0997 | 0.4128 | 1309 | 1.5261 |
| 1.8286 | 0.4718 | 1496 | 1.5064 |
| 1.5907 | 0.5307 | 1683 | 1.5066 |
| 1.2141 | 0.5897 | 1870 | 1.5087 |
| 1.1 | 0.6487 | 2057 | 1.5143 |
| 2.2702 | 0.7077 | 2244 | 1.4966 |
| 1.6695 | 0.7666 | 2431 | 1.4940 |
| 1.0971 | 0.8256 | 2618 | 1.4993 |
| 1.0334 | 0.8846 | 2805 | 1.5000 |
| 2.1121 | 0.9436 | 2992 | 1.4884 |
| 1.018 | 1.0025 | 3179 | 1.4857 |
| 2.3609 | 1.0615 | 3366 | 1.5047 |
| 1.3538 | 1.1205 | 3553 | 1.5023 |
| 1.1705 | 1.1794 | 3740 | 1.5119 |
| 0.9591 | 1.2384 | 3927 | 1.5204 |
| 1.6959 | 1.2974 | 4114 | 1.5072 |
| 1.1079 | 1.3564 | 4301 | 1.5044 |
| 0.9931 | 1.4153 | 4488 | 1.5083 |
| 1.0877 | 1.4743 | 4675 | 1.5130 |
| 1.8909 | 1.5333 | 4862 | 1.5019 |
| 1.3393 | 1.5922 | 5049 | 1.5017 |
| 0.9624 | 1.6512 | 5236 | 1.5112 |
| 0.9601 | 1.7102 | 5423 | 1.5052 |
| 1.7004 | 1.7692 | 5610 | 1.4982 |
| 1.106 | 1.8281 | 5797 | 1.4998 |
| 0.9435 | 1.8871 | 5984 | 1.4967 |
| 2.1416 | 1.9461 | 6171 | 1.4946 |
| 0.9186 | 2.0050 | 6358 | 1.4976 |
| 0.9313 | 2.0640 | 6545 | 1.6116 |
| 1.419 | 2.1230 | 6732 | 1.5636 |
| 0.9927 | 2.1820 | 6919 | 1.5573 |
| 1.0184 | 2.2409 | 7106 | 1.5744 |
| 0.9992 | 2.2999 | 7293 | 1.5949 |
| 1.1248 | 2.3589 | 7480 | 1.5689 |
| 1.1603 | 2.4178 | 7667 | 1.5694 |
| 0.9741 | 2.4768 | 7854 | 1.5818 |
| 1.0486 | 2.5358 | 8041 | 1.5601 |
| 1.4454 | 2.5948 | 8228 | 1.5503 |
| 0.9723 | 2.6537 | 8415 | 1.5504 |
| 0.8609 | 2.7127 | 8602 | 1.5705 |
| 1.5946 | 2.7717 | 8789 | 1.5788 |
| 1.2105 | 2.8307 | 8976 | 1.5532 |
| 1.0555 | 2.8896 | 9163 | 1.5667 |
| 0.8882 | 2.9486 | 9350 | 1.5810 |
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
- other
- Created
- Sep 24, 2024
- Updated
- Sep 29, 2024