End of training
Browse files- README.md +109 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- unsloth
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: meta-llama/Llama-2-13b-hf
|
| 8 |
+
model-index:
|
| 9 |
+
- name: llama_2_13b_MetaMathQA_40K_ortho
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# llama_2_13b_MetaMathQA_40K_ortho
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4660
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0001
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_steps: 0.02
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.7973 | 0.0211 | 13 | 0.6231 |
|
| 55 |
+
| 0.587 | 0.0421 | 26 | 0.5915 |
|
| 56 |
+
| 0.5618 | 0.0632 | 39 | 0.5752 |
|
| 57 |
+
| 0.5435 | 0.0842 | 52 | 0.5648 |
|
| 58 |
+
| 0.5329 | 0.1053 | 65 | 0.5548 |
|
| 59 |
+
| 0.5189 | 0.1264 | 78 | 0.5486 |
|
| 60 |
+
| 0.5265 | 0.1474 | 91 | 0.5423 |
|
| 61 |
+
| 0.507 | 0.1685 | 104 | 0.5367 |
|
| 62 |
+
| 0.5282 | 0.1896 | 117 | 0.5328 |
|
| 63 |
+
| 0.517 | 0.2106 | 130 | 0.5292 |
|
| 64 |
+
| 0.4969 | 0.2317 | 143 | 0.5249 |
|
| 65 |
+
| 0.481 | 0.2527 | 156 | 0.5207 |
|
| 66 |
+
| 0.4847 | 0.2738 | 169 | 0.5166 |
|
| 67 |
+
| 0.4876 | 0.2949 | 182 | 0.5137 |
|
| 68 |
+
| 0.4776 | 0.3159 | 195 | 0.5105 |
|
| 69 |
+
| 0.4857 | 0.3370 | 208 | 0.5071 |
|
| 70 |
+
| 0.4888 | 0.3580 | 221 | 0.5037 |
|
| 71 |
+
| 0.4833 | 0.3791 | 234 | 0.5016 |
|
| 72 |
+
| 0.4695 | 0.4002 | 247 | 0.4988 |
|
| 73 |
+
| 0.476 | 0.4212 | 260 | 0.4948 |
|
| 74 |
+
| 0.4873 | 0.4423 | 273 | 0.4931 |
|
| 75 |
+
| 0.4709 | 0.4633 | 286 | 0.4913 |
|
| 76 |
+
| 0.4765 | 0.4844 | 299 | 0.4892 |
|
| 77 |
+
| 0.4767 | 0.5055 | 312 | 0.4871 |
|
| 78 |
+
| 0.4599 | 0.5265 | 325 | 0.4856 |
|
| 79 |
+
| 0.4687 | 0.5476 | 338 | 0.4838 |
|
| 80 |
+
| 0.4525 | 0.5687 | 351 | 0.4826 |
|
| 81 |
+
| 0.4627 | 0.5897 | 364 | 0.4797 |
|
| 82 |
+
| 0.4535 | 0.6108 | 377 | 0.4781 |
|
| 83 |
+
| 0.4574 | 0.6318 | 390 | 0.4766 |
|
| 84 |
+
| 0.4597 | 0.6529 | 403 | 0.4758 |
|
| 85 |
+
| 0.4651 | 0.6740 | 416 | 0.4746 |
|
| 86 |
+
| 0.456 | 0.6950 | 429 | 0.4732 |
|
| 87 |
+
| 0.4557 | 0.7161 | 442 | 0.4720 |
|
| 88 |
+
| 0.4505 | 0.7371 | 455 | 0.4708 |
|
| 89 |
+
| 0.4446 | 0.7582 | 468 | 0.4699 |
|
| 90 |
+
| 0.4574 | 0.7793 | 481 | 0.4688 |
|
| 91 |
+
| 0.4459 | 0.8003 | 494 | 0.4678 |
|
| 92 |
+
| 0.4394 | 0.8214 | 507 | 0.4674 |
|
| 93 |
+
| 0.4587 | 0.8424 | 520 | 0.4672 |
|
| 94 |
+
| 0.4536 | 0.8635 | 533 | 0.4667 |
|
| 95 |
+
| 0.4488 | 0.8846 | 546 | 0.4666 |
|
| 96 |
+
| 0.4504 | 0.9056 | 559 | 0.4662 |
|
| 97 |
+
| 0.4428 | 0.9267 | 572 | 0.4661 |
|
| 98 |
+
| 0.4505 | 0.9478 | 585 | 0.4660 |
|
| 99 |
+
| 0.444 | 0.9688 | 598 | 0.4659 |
|
| 100 |
+
| 0.4496 | 0.9899 | 611 | 0.4660 |
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
### Framework versions
|
| 104 |
+
|
| 105 |
+
- PEFT 0.7.1
|
| 106 |
+
- Transformers 4.40.2
|
| 107 |
+
- Pytorch 2.3.0+cu121
|
| 108 |
+
- Datasets 2.19.1
|
| 109 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 125248064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:218a2dcd26feb19948129b2ba0aeda3834145aef8aa3028f9e1a94021b0cbe3d
|
| 3 |
size 125248064
|