End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: davidkim205/nox-solar-10.7b-v4
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: dpo_v4_reseve_v1
|
| 10 |
+
results: []
|
| 11 |
+
library_name: peft
|
| 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 |
+
# dpo_v4_reseve_v1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [davidkim205/nox-solar-10.7b-v4](https://huggingface.co/davidkim205/nox-solar-10.7b-v4) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.2529
|
| 22 |
+
- Rewards/chosen: 1.8018
|
| 23 |
+
- Rewards/rejected: -2.8948
|
| 24 |
+
- Rewards/accuracies: 0.5640
|
| 25 |
+
- Rewards/margins: 4.6966
|
| 26 |
+
- Logps/rejected: -431.3928
|
| 27 |
+
- Logps/chosen: -361.0608
|
| 28 |
+
- Logits/rejected: -2.2914
|
| 29 |
+
- Logits/chosen: -2.3061
|
| 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: 0.0001
|
| 49 |
+
- train_batch_size: 2
|
| 50 |
+
- eval_batch_size: 2
|
| 51 |
+
- seed: 42
|
| 52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 60 |
+
| 1.5803 | 1.0 | 4750 | 1.2529 | 1.8018 | -2.8948 | 0.5640 | 4.6966 | -431.3928 | -361.0608 | -2.2914 | -2.3061 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.5.0
|
| 66 |
+
- Transformers 4.39.3
|
| 67 |
+
- Pytorch 2.1.1+cu121
|
| 68 |
+
- Datasets 2.18.0
|
| 69 |
+
- Tokenizers 0.15.2
|