Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ Designed to serve as a virtual research assistant, providing answers to complex
|
|
19 |
## Training and Evaluation Data
|
20 |
The model was trained on a synthetic question-and-answer dataset created from academic paper abstracts in economics, employing a GPT-3.5 Turbo model for generating contextual dialogues.
|
21 |
|
22 |
-
### Training Hyperparameters
|
23 |
- **QLoRA Settings:**
|
24 |
- `lora_rank (lora_r)`: 64
|
25 |
- `lora_dropout`: 0.1
|
@@ -43,15 +43,15 @@ The model was trained on a synthetic question-and-answer dataset created from ac
|
|
43 |
|
44 |
The LLaMA-2-Econ Q&A model's performance was evaluated against a set of criteria designed to measure its effectiveness in generating accurate, relevant answers to economics-related questions. We used BERT-Score.
|
45 |
|
46 |
-
### Key Metrics
|
47 |
- **Precision:** Achieved an average precision value of **0.90**, indicating a high level of accuracy in the tokens used within the model's answers when compared to the reference answers.
|
48 |
- **Recall:** Recorded an average recall value of **0.89**, reflecting the model's ability to capture all relevant information from the reference answers in its generated responses.
|
49 |
- **F1 Score:** Reached an average F1 value of **0.90**, demonstrating an excellent balance between precision and recall, thus indicating the model's overall effectiveness in producing comprehensive and accurate answers.
|
50 |
|
51 |
-
### Evaluation Procedure
|
52 |
1. **Reference Answers Generation:** A subset of synthetically created questions was used to obtain reference answers from the base LLaMA-2-7B-chat model integrated with a Retrieval Augmented Generation (RAG) pipeline, employing semantic search and dense vector indexing.
|
53 |
2. **Human Verification:** The reference answers were subjected to human verification to ensure their relevance and accuracy.
|
54 |
3. **Model Comparison:** LLaMA-2-Econ's generated answers, produced without any RAG integration, were compared against these human-verified reference responses.
|
55 |
|
56 |
-
### Citation
|
57 |
- Keleş, O. & Bayraklı, Ö. T. (Fortcoming 2024, May). *LLaMA-2-Econ: Enhancing Title Generation, Classification, and Academic Q&A in Economic Research.* To be presented in LREC-COLING 2024, 4th Workshop on ECONLP: Turin, Italy.
|
|
|
19 |
## Training and Evaluation Data
|
20 |
The model was trained on a synthetic question-and-answer dataset created from academic paper abstracts in economics, employing a GPT-3.5 Turbo model for generating contextual dialogues.
|
21 |
|
22 |
+
### Training Hyperparameters
|
23 |
- **QLoRA Settings:**
|
24 |
- `lora_rank (lora_r)`: 64
|
25 |
- `lora_dropout`: 0.1
|
|
|
43 |
|
44 |
The LLaMA-2-Econ Q&A model's performance was evaluated against a set of criteria designed to measure its effectiveness in generating accurate, relevant answers to economics-related questions. We used BERT-Score.
|
45 |
|
46 |
+
### Key Metrics
|
47 |
- **Precision:** Achieved an average precision value of **0.90**, indicating a high level of accuracy in the tokens used within the model's answers when compared to the reference answers.
|
48 |
- **Recall:** Recorded an average recall value of **0.89**, reflecting the model's ability to capture all relevant information from the reference answers in its generated responses.
|
49 |
- **F1 Score:** Reached an average F1 value of **0.90**, demonstrating an excellent balance between precision and recall, thus indicating the model's overall effectiveness in producing comprehensive and accurate answers.
|
50 |
|
51 |
+
### Evaluation Procedure
|
52 |
1. **Reference Answers Generation:** A subset of synthetically created questions was used to obtain reference answers from the base LLaMA-2-7B-chat model integrated with a Retrieval Augmented Generation (RAG) pipeline, employing semantic search and dense vector indexing.
|
53 |
2. **Human Verification:** The reference answers were subjected to human verification to ensure their relevance and accuracy.
|
54 |
3. **Model Comparison:** LLaMA-2-Econ's generated answers, produced without any RAG integration, were compared against these human-verified reference responses.
|
55 |
|
56 |
+
### Citation
|
57 |
- Keleş, O. & Bayraklı, Ö. T. (Fortcoming 2024, May). *LLaMA-2-Econ: Enhancing Title Generation, Classification, and Academic Q&A in Economic Research.* To be presented in LREC-COLING 2024, 4th Workshop on ECONLP: Turin, Italy.
|