End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: gemma
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: adl-hw3-finetune-gemma-2-chinese-kyara-10
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# adl-hw3-finetune-gemma-2-chinese-kyara-10
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [zake7749/gemma-2-2b-it-chinese-kyara-dpo](https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.3204
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 4
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 52 |
+
| 2.4837 | 0.3556 | 200 | 2.2732 |
|
| 53 |
+
| 2.2305 | 0.7111 | 400 | 2.1807 |
|
| 54 |
+
| 2.1064 | 1.0667 | 600 | 2.1585 |
|
| 55 |
+
| 1.8998 | 1.4222 | 800 | 2.1417 |
|
| 56 |
+
| 1.9278 | 1.7778 | 1000 | 2.1226 |
|
| 57 |
+
| 1.7739 | 2.1333 | 1200 | 2.1940 |
|
| 58 |
+
| 1.5948 | 2.4889 | 1400 | 2.1968 |
|
| 59 |
+
| 1.6098 | 2.8444 | 1600 | 2.1953 |
|
| 60 |
+
| 1.5028 | 3.2 | 1800 | 2.3265 |
|
| 61 |
+
| 1.3777 | 3.5556 | 2000 | 2.3321 |
|
| 62 |
+
| 1.3716 | 3.9111 | 2200 | 2.3204 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- PEFT 0.13.2
|
| 68 |
+
- Transformers 4.45.1
|
| 69 |
+
- Pytorch 2.5.0+cu121
|
| 70 |
+
- Datasets 3.1.0
|
| 71 |
+
- Tokenizers 0.20.3
|