Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -62,26 +62,26 @@ outputs = model.generate(
|
|
| 62 |
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 63 |
print(generated_text)
|
| 64 |
|
| 65 |
-
### Explanation:
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
|
| 87 |
|
|
|
|
| 62 |
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 63 |
print(generated_text)
|
| 64 |
|
| 65 |
+
#### Explanation:
|
| 66 |
+
|
| 67 |
+
Training Data
|
| 68 |
+
The model was fine-tuned using the Alpaca GPT-4 dataset available at the following GitHub repository.
|
| 69 |
+
https://github.com/hy5468/TransLLM/tree/main/data/train
|
| 70 |
+
Specifically, the alpaca_gpt4_data_en.zip dataset was utilized.
|
| 71 |
+
This dataset includes a wide range of instruction-based prompts and responses,
|
| 72 |
+
providing a robust foundation for the model's training.
|
| 73 |
+
|
| 74 |
+
Training Procedure
|
| 75 |
+
The fine-tuning process was carried out with the following hyperparameters:
|
| 76 |
+
Learning Rate: 2e-5
|
| 77 |
+
Batch Size (Train): 4
|
| 78 |
+
Batch Size (Eval): 4
|
| 79 |
+
Number of Epochs: 1
|
| 80 |
+
Weight Decay: 0.01
|
| 81 |
+
|
| 82 |
+
Training Environment
|
| 83 |
+
The model was trained using PyTorch and the Hugging Face transformers library.
|
| 84 |
+
The training was performed on a GPU-enabled environment to accelerate the fine-tuning process.
|
| 85 |
+
The training script ensures reproducibility by setting a consistent random seed across different components.
|
| 86 |
|
| 87 |
|