Model save
Browse files- README.md +72 -0
- adapter_model.safetensors +2 -2
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-Agents-Zephyr-1.0.1-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-Agents-Zephyr-1.0.1-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: 0.4733
|
| 22 |
+
- Rewards/chosen: -188.7491
|
| 23 |
+
- Logps/chosen: -2394.6819
|
| 24 |
+
- Rewards/rejected: -176.6560
|
| 25 |
+
- Logps/rejected: -2418.2639
|
| 26 |
+
- Kl: 0.0
|
| 27 |
+
- Rewards/margins: -12.4013
|
| 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: 4
|
| 48 |
+
- eval_batch_size: 4
|
| 49 |
+
- seed: 42
|
| 50 |
+
- gradient_accumulation_steps: 4
|
| 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: 145
|
| 56 |
+
- mixed_precision_training: Native AMP
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Logps/chosen | Rewards/rejected | Logps/rejected | Kl | Rewards/margins |
|
| 61 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------:|:----------------:|:--------------:|:-------:|:---------------:|
|
| 62 |
+
| 0.5465 | 0.34 | 50 | 0.5112 | -20.3414 | -710.6042 | -4.1466 | -693.1708 | 45.8506 | -17.1827 |
|
| 63 |
+
| 0.4745 | 0.68 | 100 | 0.4733 | -188.7491 | -2394.6819 | -176.6560 | -2418.2639 | 0.0 | -12.4013 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- PEFT 0.10.0
|
| 69 |
+
- Transformers 4.39.1
|
| 70 |
+
- Pytorch 2.1.0+cu118
|
| 71 |
+
- Datasets 2.18.0
|
| 72 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b3b9fd6ac115d040e39d1eff22a9e0c8f47ecb5ec1d98d80cddfcfa1466ef23
|
| 3 |
+
size 1103203256
|