Commit
•
ebe73b4
1
Parent(s):
02a34b9
Tayyab-444/openhermes-mistral-dpo-gptq
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- dpo
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: openhermes-mistral-dpo-gptq
|
| 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 |
+
# openhermes-mistral-dpo-gptq
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.9029
|
| 22 |
+
- Rewards/chosen: -0.1592
|
| 23 |
+
- Rewards/rejected: -0.0751
|
| 24 |
+
- Rewards/accuracies: 0.4375
|
| 25 |
+
- Rewards/margins: -0.0841
|
| 26 |
+
- Logps/rejected: -164.9728
|
| 27 |
+
- Logps/chosen: -207.7616
|
| 28 |
+
- Logits/rejected: -2.4937
|
| 29 |
+
- Logits/chosen: -2.5880
|
| 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: 1
|
| 50 |
+
- eval_batch_size: 8
|
| 51 |
+
- seed: 42
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- lr_scheduler_warmup_steps: 2
|
| 55 |
+
- training_steps: 50
|
| 56 |
+
- mixed_precision_training: Native AMP
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 61 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 62 |
+
| 0.6777 | 0.005 | 10 | 0.7136 | -0.0128 | -0.0514 | 0.5625 | 0.0386 | -164.7356 | -206.2971 | -2.4991 | -2.5809 |
|
| 63 |
+
| 0.6983 | 0.01 | 20 | 0.7209 | -0.0223 | -0.1062 | 0.625 | 0.0838 | -165.2831 | -206.3929 | -2.4962 | -2.5809 |
|
| 64 |
+
| 0.697 | 0.015 | 30 | 0.7341 | -0.0064 | -0.0583 | 0.6875 | 0.0519 | -164.8043 | -206.2330 | -2.4984 | -2.5864 |
|
| 65 |
+
| 0.6967 | 0.02 | 40 | 0.7473 | -0.0052 | -0.0485 | 0.4375 | 0.0433 | -164.7064 | -206.2214 | -2.4930 | -2.5857 |
|
| 66 |
+
| 0.6666 | 0.025 | 50 | 0.9029 | -0.1592 | -0.0751 | 0.4375 | -0.0841 | -164.9728 | -207.7616 | -2.4937 | -2.5880 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.12.0
|
| 72 |
+
- Transformers 4.42.4
|
| 73 |
+
- Pytorch 2.0.1+cu117
|
| 74 |
+
- Datasets 2.20.0
|
| 75 |
+
- Tokenizers 0.19.1
|