Model save
Browse files- README.md +90 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- kto
|
| 7 |
+
- KTO
|
| 8 |
+
- WeniGPT
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
base_model: HuggingFaceH4/zephyr-7b-beta
|
| 11 |
+
model-index:
|
| 12 |
+
- name: kto-test
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# kto-test
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.0147
|
| 24 |
+
- Rewards/chosen: 5.6143
|
| 25 |
+
- Rewards/rejected: -31.0540
|
| 26 |
+
- Rewards/margins: 36.6683
|
| 27 |
+
- Kl: 0.0
|
| 28 |
+
- Logps/chosen: -130.3461
|
| 29 |
+
- Logps/rejected: -503.4655
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 0.0002
|
| 49 |
+
- train_batch_size: 2
|
| 50 |
+
- eval_batch_size: 2
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- num_devices: 2
|
| 54 |
+
- gradient_accumulation_steps: 8
|
| 55 |
+
- total_train_batch_size: 32
|
| 56 |
+
- total_eval_batch_size: 4
|
| 57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
+
- lr_scheduler_type: linear
|
| 59 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 60 |
+
- training_steps: 786
|
| 61 |
+
- mixed_precision_training: Native AMP
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/margins | Kl | Logps/chosen | Logps/rejected |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:---------------:|:------:|:------------:|:--------------:|
|
| 67 |
+
| 371.0873 | 0.38 | 50 | 0.0440 | 4.6808 | -9.5189 | 14.1997 | 0.0150 | -139.6814 | -288.1148 |
|
| 68 |
+
| 57.9834 | 0.76 | 100 | 0.0275 | 5.1394 | -31.8945 | 37.0339 | 0.0 | -135.0947 | -511.8704 |
|
| 69 |
+
| 37.3685 | 1.14 | 150 | 0.0196 | 5.2556 | -27.1934 | 32.4491 | 0.0 | -133.9325 | -464.8599 |
|
| 70 |
+
| 3.6561 | 1.52 | 200 | 0.0162 | 5.4306 | -22.6310 | 28.0615 | 0.0 | -132.1833 | -419.2354 |
|
| 71 |
+
| 59.5367 | 1.9 | 250 | 0.0143 | 5.7355 | -31.1619 | 36.8974 | 0.0 | -129.1339 | -504.5448 |
|
| 72 |
+
| 13.1891 | 2.29 | 300 | 0.0147 | 5.6143 | -31.0540 | 36.6683 | 0.0 | -130.3461 | -503.4655 |
|
| 73 |
+
| 3.8532 | 2.67 | 350 | 0.0131 | 5.8860 | -26.4154 | 32.3014 | 0.0 | -127.6289 | -457.0801 |
|
| 74 |
+
| 3.7678 | 3.05 | 400 | 0.0162 | 5.9318 | -26.7524 | 32.6841 | 0.0 | -127.1711 | -460.4493 |
|
| 75 |
+
| 49.3456 | 3.43 | 450 | 0.0167 | 5.9252 | -28.7033 | 34.6286 | 0.0 | -127.2365 | -479.9590 |
|
| 76 |
+
| 12.2886 | 3.81 | 500 | 0.0164 | 6.0009 | -29.4493 | 35.4501 | 0.0 | -126.4803 | -487.4185 |
|
| 77 |
+
| 2.3745 | 4.19 | 550 | 0.0173 | 6.0124 | -29.9808 | 35.9932 | 0.0 | -126.3649 | -492.7338 |
|
| 78 |
+
| 0.46 | 4.57 | 600 | 0.0173 | 6.0060 | -30.4606 | 36.4666 | 0.0 | -126.4293 | -497.5318 |
|
| 79 |
+
| 7.7723 | 4.95 | 650 | 0.0180 | 6.0079 | -30.7030 | 36.7109 | 0.0 | -126.4096 | -499.9554 |
|
| 80 |
+
| 4.1333 | 5.33 | 700 | 0.0184 | 6.0037 | -30.8948 | 36.8984 | 0.0 | -126.4521 | -501.8734 |
|
| 81 |
+
| 1.6938 | 5.71 | 750 | 0.0183 | 6.0119 | -30.9672 | 36.9791 | 0.0 | -126.3704 | -502.5979 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- PEFT 0.10.0
|
| 87 |
+
- Transformers 4.39.1
|
| 88 |
+
- Pytorch 2.1.0+cu118
|
| 89 |
+
- Datasets 2.18.0
|
| 90 |
+
- Tokenizers 0.15.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 54560368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:031a5f6a211c4d959812a095eca9b1fe8976417fcaa8fdfd907151ccff1f6bfe
|
| 3 |
size 54560368
|