---
license: other
base_model: Qwen/Qwen1.5-4B
tags:
- generated_from_trainer
datasets:
- tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
metrics:
- accuracy
model-index:
- name: lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_3e-5_lora2
  results:
  - task:
      name: Causal Language Modeling
      type: text-generation
    dataset:
      name: tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
      type: tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.7263318777292577
library_name: peft
---

<!-- 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_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_3e-5_lora2

This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on the tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9440
- Accuracy: 0.7263

## 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: 3e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 20.0

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
| 1.584         | 0.9998  | 1089  | 1.5103          | 0.6762   |
| 1.5504        | 1.9995  | 2178  | 1.4772          | 0.6791   |
| 1.4842        | 2.9993  | 3267  | 1.4502          | 0.6812   |
| 1.427         | 4.0     | 4357  | 1.4200          | 0.6837   |
| 1.3827        | 4.9998  | 5446  | 1.3911          | 0.6860   |
| 1.3425        | 5.9995  | 6535  | 1.3615          | 0.6887   |
| 1.2738        | 6.9993  | 7624  | 1.3300          | 0.6910   |
| 1.2283        | 8.0     | 8714  | 1.3020          | 0.6935   |
| 1.1788        | 8.9998  | 9803  | 1.2722          | 0.6963   |
| 1.1156        | 9.9995  | 10892 | 1.2415          | 0.6990   |
| 1.0526        | 10.9993 | 11981 | 1.2131          | 0.7015   |
| 1.0146        | 12.0    | 13071 | 1.1804          | 0.7045   |
| 0.9613        | 12.9998 | 14160 | 1.1508          | 0.7071   |
| 0.9109        | 13.9995 | 15249 | 1.1214          | 0.7097   |
| 0.8566        | 14.9993 | 16338 | 1.0913          | 0.7128   |
| 0.8307        | 16.0    | 17428 | 1.0599          | 0.7156   |
| 0.7803        | 16.9998 | 18517 | 1.0283          | 0.7184   |
| 0.7486        | 17.9995 | 19606 | 0.9997          | 0.7215   |
| 0.6992        | 18.9993 | 20695 | 0.9719          | 0.7238   |
| 0.6632        | 19.9954 | 21780 | 0.9440          | 0.7263   |


### Framework versions

- PEFT 0.5.0
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1