Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- kto
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: HuggingFaceH4/zephyr-7b-beta
|
| 9 |
+
model-index:
|
| 10 |
+
- name: WeniGPT-QA-Zephyr-7B-4.0.0-KTO
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# WeniGPT-QA-Zephyr-7B-4.0.0-KTO
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0172
|
| 22 |
+
- Rewards/chosen: 5.2018
|
| 23 |
+
- Rewards/rejected: -101.1277
|
| 24 |
+
- Rewards/margins: 106.3295
|
| 25 |
+
- Kl: 0.6591
|
| 26 |
+
- Logps/chosen: -123.7008
|
| 27 |
+
- Logps/rejected: -1204.3472
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 0.0002
|
| 47 |
+
- train_batch_size: 2
|
| 48 |
+
- eval_batch_size: 2
|
| 49 |
+
- seed: 42
|
| 50 |
+
- gradient_accumulation_steps: 8
|
| 51 |
+
- total_train_batch_size: 16
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 55 |
+
- training_steps: 786
|
| 56 |
+
- mixed_precision_training: Native AMP
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/margins | Kl | Logps/chosen | Logps/rejected |
|
| 61 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:---------------:|:------:|:------------:|:--------------:|
|
| 62 |
+
| 124.9389 | 0.19 | 50 | 0.0980 | 4.3712 | -4.4622 | 8.8334 | 3.2830 | -132.0074 | -237.6924 |
|
| 63 |
+
| 10.8269 | 0.38 | 100 | 0.0399 | 4.0267 | -34.8306 | 38.8572 | 0.7623 | -135.4527 | -541.3764 |
|
| 64 |
+
| 276.3512 | 0.57 | 150 | 0.0280 | 4.7987 | -20.4823 | 25.2810 | 1.6861 | -127.7321 | -397.8935 |
|
| 65 |
+
| 5.7214 | 0.76 | 200 | 0.0299 | 5.0010 | -21.9689 | 26.9699 | 1.5452 | -125.7095 | -412.7599 |
|
| 66 |
+
| 207.9747 | 0.94 | 250 | 0.0262 | 4.8172 | -61.3154 | 66.1326 | 1.1824 | -127.5472 | -806.2249 |
|
| 67 |
+
| 25.0348 | 1.13 | 300 | 0.0206 | 4.9858 | -70.8381 | 75.8240 | 1.4845 | -125.8608 | -901.4517 |
|
| 68 |
+
| 3.1951 | 1.32 | 350 | 0.0265 | 4.6896 | -82.7767 | 87.4663 | 0.6364 | -128.8232 | -1020.8375 |
|
| 69 |
+
| 68.7248 | 1.51 | 400 | 0.0201 | 5.0567 | -53.7706 | 58.8272 | 1.2176 | -125.1527 | -730.7762 |
|
| 70 |
+
| 10.659 | 1.7 | 450 | 0.0263 | 4.9077 | -76.2636 | 81.1714 | 0.8826 | -126.6419 | -955.7070 |
|
| 71 |
+
| 177.5836 | 1.89 | 500 | 0.0187 | 5.1836 | -82.5033 | 87.6869 | 0.4794 | -123.8830 | -1018.1035 |
|
| 72 |
+
| 15.4933 | 2.08 | 550 | 0.0281 | 4.7980 | -95.1968 | 99.9948 | 0.9202 | -127.7392 | -1145.0382 |
|
| 73 |
+
| 3.827 | 2.27 | 600 | 0.0178 | 5.0335 | -96.9958 | 102.0293 | 0.4925 | -125.3841 | -1163.0284 |
|
| 74 |
+
| 16.3759 | 2.45 | 650 | 0.0194 | 5.1136 | -106.3420 | 111.4556 | 0.6069 | -124.5831 | -1256.4906 |
|
| 75 |
+
| 7.4087 | 2.64 | 700 | 0.0172 | 5.2018 | -101.1277 | 106.3295 | 0.6591 | -123.7008 | -1204.3472 |
|
| 76 |
+
| 23.8901 | 2.83 | 750 | 0.0177 | 5.2007 | -102.1235 | 107.3241 | 0.6737 | -123.7124 | -1214.3054 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- PEFT 0.10.0
|
| 82 |
+
- Transformers 4.39.1
|
| 83 |
+
- Pytorch 2.1.0+cu118
|
| 84 |
+
- Datasets 2.18.0
|
| 85 |
+
- Tokenizers 0.15.2
|