Update README.md
Browse files
README.md
CHANGED
|
@@ -43,4 +43,20 @@ https://github.com/hiyouga/LLaMA-Factory
|
|
| 43 |
- https://huggingface.co/datasets/LooksJuicy/ruozhiba
|
| 44 |
- https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k
|
| 45 |
- https://huggingface.co/datasets/alexl83/AlpacaDataCleaned
|
| 46 |
-
- https://huggingface.co/datasets/Sao10K/Claude-3-Opus-Instruct-5K
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
- https://huggingface.co/datasets/LooksJuicy/ruozhiba
|
| 44 |
- https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k
|
| 45 |
- https://huggingface.co/datasets/alexl83/AlpacaDataCleaned
|
| 46 |
+
- https://huggingface.co/datasets/Sao10K/Claude-3-Opus-Instruct-5K
|
| 47 |
+
|
| 48 |
+
### Training hyperparameters
|
| 49 |
+
The following hyperparameters were used during training:
|
| 50 |
+
- learning_rate: 5e-05
|
| 51 |
+
- train_batch_size: 4
|
| 52 |
+
- eval_batch_size: 8
|
| 53 |
+
- seed: 42
|
| 54 |
+
- distributed_type: multi-GPU
|
| 55 |
+
- num_devices: 8
|
| 56 |
+
- gradient_accumulation_steps: 4
|
| 57 |
+
- total_train_batch_size: 128
|
| 58 |
+
- total_eval_batch_size: 64
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: cosine
|
| 61 |
+
- lr_scheduler_warmup_steps: 300
|
| 62 |
+
- num_epochs: 1.0
|