Update README.md
Browse files
README.md
CHANGED
@@ -60,7 +60,7 @@ This model utilizes the `MistralForCausalLM` architecture with a `LlamaTokenizer
|
|
60 |
|
61 |
## Training Data
|
62 |
|
63 |
-
The model was fine-tuned on the [Bitext Insurance Dataset](https://huggingface.co/datasets/bitext/Bitext-insurance-llm-chatbot-training-dataset) comprising various insurance-related intents, including: buy_insurance_policy, schedule_appointment, check_payments, calculate_insurance_quote, negotiate_settlement,
|
64 |
|
65 |
This comprehensive training helps the model address a broad spectrum of insurance-related questions effectively. The dataset follows the same structured approach as our dataset published on Hugging Face as [bitext/Bitext-customer-support-llm-chatbot-training-dataset](https://huggingface.co/datasets/bitext/Bitext-customer-support-llm-chatbot-training-dataset), but with a focus on insurance.
|
66 |
|
@@ -70,7 +70,7 @@ This comprehensive training helps the model address a broad spectrum of insuranc
|
|
70 |
|
71 |
- **Optimizer**: AdamW
|
72 |
- **Learning Rate**: 0.0002 with a cosine learning rate scheduler
|
73 |
-
- **Epochs**:
|
74 |
- **Batch Size**: 4
|
75 |
- **Gradient Accumulation Steps**: 4
|
76 |
- **Maximum Sequence Length**: 8192 tokens
|
|
|
60 |
|
61 |
## Training Data
|
62 |
|
63 |
+
The model was fine-tuned on the [Bitext Insurance Dataset](https://huggingface.co/datasets/bitext/Bitext-insurance-llm-chatbot-training-dataset) comprising various insurance-related intents, including: buy_insurance_policy, schedule_appointment, check_payments, calculate_insurance_quote, negotiate_settlement, and more. Totaling 39 intents, and each intent is represented by approximately 1000 examples.
|
64 |
|
65 |
This comprehensive training helps the model address a broad spectrum of insurance-related questions effectively. The dataset follows the same structured approach as our dataset published on Hugging Face as [bitext/Bitext-customer-support-llm-chatbot-training-dataset](https://huggingface.co/datasets/bitext/Bitext-customer-support-llm-chatbot-training-dataset), but with a focus on insurance.
|
66 |
|
|
|
70 |
|
71 |
- **Optimizer**: AdamW
|
72 |
- **Learning Rate**: 0.0002 with a cosine learning rate scheduler
|
73 |
+
- **Epochs**: 1
|
74 |
- **Batch Size**: 4
|
75 |
- **Gradient Accumulation Steps**: 4
|
76 |
- **Maximum Sequence Length**: 8192 tokens
|