Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: microsoft/Orca-2-13b
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: qlora-out
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 15 |
+
# qlora-out
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9190
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 2
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 10
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
+
| No log | 0.0 | 1 | 3.2585 |
|
| 54 |
+
| 1.9811 | 0.05 | 536 | 2.0113 |
|
| 55 |
+
| 1.9507 | 0.1 | 1072 | 1.9877 |
|
| 56 |
+
| 1.9576 | 0.15 | 1608 | 1.9766 |
|
| 57 |
+
| 1.9308 | 0.2 | 2144 | 1.9671 |
|
| 58 |
+
| 1.9193 | 0.25 | 2680 | 1.9597 |
|
| 59 |
+
| 1.8522 | 0.3 | 3216 | 1.9530 |
|
| 60 |
+
| 1.895 | 0.35 | 3752 | 1.9483 |
|
| 61 |
+
| 1.869 | 0.4 | 4288 | 1.9432 |
|
| 62 |
+
| 1.8664 | 0.45 | 4824 | 1.9383 |
|
| 63 |
+
| 1.8661 | 0.5 | 5360 | 1.9347 |
|
| 64 |
+
| 1.8576 | 0.55 | 5896 | 1.9337 |
|
| 65 |
+
| 1.8573 | 0.6 | 6432 | 1.9286 |
|
| 66 |
+
| 1.8665 | 0.65 | 6968 | 1.9280 |
|
| 67 |
+
| 1.8429 | 0.7 | 7504 | 1.9243 |
|
| 68 |
+
| 1.8621 | 0.75 | 8040 | 1.9221 |
|
| 69 |
+
| 1.8074 | 0.8 | 8576 | 1.9209 |
|
| 70 |
+
| 1.8199 | 0.85 | 9112 | 1.9202 |
|
| 71 |
+
| 1.8733 | 0.9 | 9648 | 1.9193 |
|
| 72 |
+
| 1.8387 | 0.95 | 10184 | 1.9190 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.35.1
|
| 78 |
+
- Pytorch 2.1.0+cu121
|
| 79 |
+
- Datasets 2.14.7
|
| 80 |
+
- Tokenizers 0.14.1
|