End of training
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 24 |
# ADL_Gemma5
|
| 25 |
|
| 26 |
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 an unknown dataset.
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -51,6 +53,17 @@ The following hyperparameters were used during training:
|
|
| 51 |
- lr_scheduler_warmup_ratio: 0.03
|
| 52 |
- num_epochs: 5
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- PEFT 0.13.2
|
|
|
|
| 24 |
# ADL_Gemma5
|
| 25 |
|
| 26 |
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 an unknown dataset.
|
| 27 |
+
It achieves the following results on the evaluation set:
|
| 28 |
+
- Loss: 1.3316
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 53 |
- lr_scheduler_warmup_ratio: 0.03
|
| 54 |
- num_epochs: 5
|
| 55 |
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 1.3857 | 1.0 | 1250 | 1.3430 |
|
| 61 |
+
| 1.3912 | 2.0 | 2500 | 1.3419 |
|
| 62 |
+
| 1.3708 | 3.0 | 3750 | 1.3364 |
|
| 63 |
+
| 1.3721 | 4.0 | 5000 | 1.3333 |
|
| 64 |
+
| 1.3663 | 5.0 | 6250 | 1.3316 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- PEFT 0.13.2
|