---
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: google/gemma-7b
metrics:
- accuracy
model-index:
- name: patent_classification_abstract
  results: []
---

<!-- 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. -->

# patent_classification_abstract

This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8488
- Accuracy: 0.711
- F1 Macro: 0.6822
- F1 Micro: 0.711

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
| 1.3887        | 0.13  | 100  | 1.1602          | 0.5952   | 0.5023   | 0.5952   |
| 0.9929        | 0.26  | 200  | 1.0044          | 0.6798   | 0.5950   | 0.6798   |
| 0.9516        | 0.38  | 300  | 1.0115          | 0.6674   | 0.6181   | 0.6674   |
| 0.8969        | 0.51  | 400  | 0.9224          | 0.6812   | 0.6056   | 0.6812   |
| 0.9096        | 0.64  | 500  | 0.8875          | 0.6998   | 0.6543   | 0.6998   |
| 0.9188        | 0.77  | 600  | 0.8629          | 0.7084   | 0.6420   | 0.7084   |
| 0.8811        | 0.9   | 700  | 0.9744          | 0.6868   | 0.6333   | 0.6868   |
| 0.6586        | 1.02  | 800  | 0.9164          | 0.7108   | 0.6736   | 0.7108   |
| 0.5782        | 1.15  | 900  | 0.8981          | 0.7112   | 0.6706   | 0.7112   |
| 0.61          | 1.28  | 1000 | 0.9286          | 0.7084   | 0.6423   | 0.7084   |
| 0.6072        | 1.41  | 1100 | 0.9468          | 0.699    | 0.6680   | 0.699    |
| 0.5666        | 1.53  | 1200 | 0.9002          | 0.711    | 0.6796   | 0.711    |
| 0.6609        | 1.66  | 1300 | 0.8995          | 0.6976   | 0.6747   | 0.6976   |
| 0.6154        | 1.79  | 1400 | 0.8488          | 0.711    | 0.6822   | 0.711    |
| 0.568         | 1.92  | 1500 | 0.8619          | 0.715    | 0.6721   | 0.715    |
| 0.2012        | 2.05  | 1600 | 1.0896          | 0.711    | 0.6735   | 0.711    |
| 0.1887        | 2.17  | 1700 | 1.1415          | 0.7      | 0.6713   | 0.7      |
| 0.2031        | 2.3   | 1800 | 1.2597          | 0.697    | 0.6651   | 0.697    |
| 0.1328        | 2.43  | 1900 | 1.2529          | 0.7098   | 0.6791   | 0.7098   |
| 0.1365        | 2.56  | 2000 | 1.2157          | 0.705    | 0.6801   | 0.705    |
| 0.1348        | 2.69  | 2100 | 1.2697          | 0.7096   | 0.6746   | 0.7096   |
| 0.1279        | 2.81  | 2200 | 1.2693          | 0.7054   | 0.6751   | 0.7054   |
| 0.1113        | 2.94  | 2300 | 1.2733          | 0.7082   | 0.6800   | 0.7082   |


### Framework versions

- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2