---
base_model: microsoft/mdeberta-v3-base
datasets:
- massive
library_name: transformers
license: mit
metrics:
- accuracy
- f1
tags:
- generated_from_trainer
model-index:
- name: scenario-NON-KD-SCR-D2_data-AmazonScience_massive_all_1_155
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: massive
      type: massive
      config: all_1.1
      split: validation
      args: all_1.1
    metrics:
    - type: accuracy
      value: 0.8146070604260471
      name: Accuracy
    - type: f1
      value: 0.7894820718803818
      name: F1
---

<!-- 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. -->

# scenario-NON-KD-SCR-D2_data-AmazonScience_massive_all_1_155

This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the massive dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9705
- Accuracy: 0.8146
- F1: 0.7895

## 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: 32
- eval_batch_size: 32
- seed: 55
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch  | Step   | Validation Loss | Accuracy | F1     |
|:-------------:|:------:|:------:|:---------------:|:--------:|:------:|
| 1.2731        | 0.2672 | 5000   | 1.2901          | 0.6543   | 0.5621 |
| 0.9748        | 0.5344 | 10000  | 0.9900          | 0.7385   | 0.6906 |
| 0.8375        | 0.8017 | 15000  | 0.8798          | 0.7648   | 0.7104 |
| 0.5776        | 1.0689 | 20000  | 0.8718          | 0.7814   | 0.7300 |
| 0.5844        | 1.3361 | 25000  | 0.8115          | 0.7917   | 0.7475 |
| 0.5128        | 1.6033 | 30000  | 0.8029          | 0.7986   | 0.7618 |
| 0.5164        | 1.8706 | 35000  | 0.7975          | 0.7978   | 0.7526 |
| 0.3296        | 2.1378 | 40000  | 0.8562          | 0.8030   | 0.7669 |
| 0.356         | 2.4050 | 45000  | 0.8397          | 0.8052   | 0.7660 |
| 0.3481        | 2.6722 | 50000  | 0.8293          | 0.8111   | 0.7798 |
| 0.3435        | 2.9394 | 55000  | 0.8290          | 0.8091   | 0.7780 |
| 0.2186        | 3.2067 | 60000  | 0.9522          | 0.8106   | 0.7777 |
| 0.2362        | 3.4739 | 65000  | 0.9482          | 0.8115   | 0.7782 |
| 0.2341        | 3.7411 | 70000  | 0.9290          | 0.8097   | 0.7801 |
| 0.2062        | 4.0083 | 75000  | 0.9605          | 0.8145   | 0.7868 |
| 0.1568        | 4.2756 | 80000  | 1.0468          | 0.8117   | 0.7825 |
| 0.1572        | 4.5428 | 85000  | 1.1166          | 0.8109   | 0.7838 |
| 0.1591        | 4.8100 | 90000  | 1.0949          | 0.8111   | 0.7859 |
| 0.0872        | 5.0772 | 95000  | 1.2311          | 0.8129   | 0.7868 |
| 0.0978        | 5.3444 | 100000 | 1.3205          | 0.8064   | 0.7780 |
| 0.104         | 5.6117 | 105000 | 1.2794          | 0.8124   | 0.7842 |
| 0.1035        | 5.8789 | 110000 | 1.2706          | 0.8140   | 0.7871 |
| 0.0615        | 6.1461 | 115000 | 1.4577          | 0.8114   | 0.7851 |
| 0.0692        | 6.4133 | 120000 | 1.4930          | 0.8097   | 0.7866 |
| 0.0662        | 6.6806 | 125000 | 1.5160          | 0.8125   | 0.7887 |
| 0.0685        | 6.9478 | 130000 | 1.5319          | 0.8124   | 0.7873 |
| 0.0481        | 7.2150 | 135000 | 1.6618          | 0.8107   | 0.7871 |
| 0.0448        | 7.4822 | 140000 | 1.7140          | 0.8119   | 0.7864 |
| 0.0405        | 7.7495 | 145000 | 1.7438          | 0.8141   | 0.7894 |
| 0.0303        | 8.0167 | 150000 | 1.8255          | 0.8116   | 0.7850 |
| 0.025         | 8.2839 | 155000 | 1.8547          | 0.8135   | 0.7898 |
| 0.0302        | 8.5511 | 160000 | 1.8674          | 0.8150   | 0.7891 |
| 0.0293        | 8.8183 | 165000 | 1.8820          | 0.8131   | 0.7890 |
| 0.0177        | 9.0856 | 170000 | 1.9414          | 0.8140   | 0.7906 |
| 0.0164        | 9.3528 | 175000 | 1.9824          | 0.8130   | 0.7898 |
| 0.019         | 9.6200 | 180000 | 1.9458          | 0.8139   | 0.7889 |
| 0.0203        | 9.8872 | 185000 | 1.9705          | 0.8146   | 0.7895 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.19.1