---
license: llama2
base_model: meta-llama/Llama-2-7b-chat-hf
tags:
- generated_from_trainer
datasets:
- tyzhu/lmind_nq_train6000_eval6489_v1_qa
metrics:
- accuracy
model-index:
- name: lmind_nq_train6000_eval6489_v1_qa_meta-llama_Llama-2-7b-chat-hf_lora2
  results:
  - task:
      name: Causal Language Modeling
      type: text-generation
    dataset:
      name: tyzhu/lmind_nq_train6000_eval6489_v1_qa
      type: tyzhu/lmind_nq_train6000_eval6489_v1_qa
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.5974358974358974
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# lmind_nq_train6000_eval6489_v1_qa_meta-llama_Llama-2-7b-chat-hf_lora2

This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the tyzhu/lmind_nq_train6000_eval6489_v1_qa dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9837
- Accuracy: 0.5974

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.8687        | 1.0   | 187  | 1.3245          | 0.6109   |
| 1.2052        | 2.0   | 375  | 1.3271          | 0.6131   |
| 0.9568        | 3.0   | 562  | 1.4014          | 0.6095   |
| 0.7696        | 4.0   | 750  | 1.5195          | 0.6054   |
| 0.6348        | 5.0   | 937  | 1.6407          | 0.6016   |
| 0.5592        | 6.0   | 1125 | 1.7334          | 0.5997   |
| 0.5166        | 7.0   | 1312 | 1.8043          | 0.5997   |
| 0.4911        | 8.0   | 1500 | 1.9042          | 0.5991   |
| 0.4494        | 9.0   | 1687 | 1.9244          | 0.5984   |
| 0.4399        | 9.97  | 1870 | 1.9837          | 0.5974   |


### Framework versions

- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1