---
license: cc-by-nc-sa-4.0
base_model: audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ft-wav2vec2-with-minds
  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. -->

# ft-wav2vec2-with-minds

This model is a fine-tuned version of [audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim](https://huggingface.co/audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2564
- Accuracy: 0.9400

## 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: 4e-05
- train_batch_size: 120
- eval_batch_size: 120
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 480
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.0796        | 1.0   | 9    | 2.0809          | 0.1209   |
| 2.0789        | 2.0   | 18   | 2.0779          | 0.1406   |
| 2.0762        | 3.0   | 27   | 2.0724          | 0.1987   |
| 2.0712        | 4.0   | 36   | 2.0627          | 0.2315   |
| 2.0601        | 5.0   | 45   | 2.0423          | 0.3327   |
| 2.0489        | 6.0   | 54   | 1.9888          | 0.5145   |
| 2.0094        | 7.0   | 63   | 1.8840          | 0.6214   |
| 1.9088        | 8.0   | 72   | 1.7428          | 0.6429   |
| 1.7904        | 9.0   | 81   | 1.5916          | 0.6448   |
| 1.6668        | 10.0  | 90   | 1.4391          | 0.7029   |
| 1.5889        | 11.0  | 99   | 1.3026          | 0.7591   |
| 1.4522        | 12.0  | 108  | 1.1715          | 0.7901   |
| 1.3301        | 13.0  | 117  | 1.0506          | 0.8257   |
| 1.2325        | 14.0  | 126  | 0.9515          | 0.8472   |
| 1.1669        | 15.0  | 135  | 0.8527          | 0.8557   |
| 1.0915        | 16.0  | 144  | 0.7745          | 0.8697   |
| 1.0157        | 17.0  | 153  | 0.7060          | 0.8772   |
| 0.9657        | 18.0  | 162  | 0.6602          | 0.8744   |
| 0.8975        | 19.0  | 171  | 0.6002          | 0.8903   |
| 0.8403        | 20.0  | 180  | 0.5651          | 0.8932   |
| 0.8059        | 21.0  | 189  | 0.5243          | 0.8960   |
| 0.731         | 22.0  | 198  | 0.4860          | 0.9044   |
| 0.7139        | 23.0  | 207  | 0.4634          | 0.9044   |
| 0.6903        | 24.0  | 216  | 0.4450          | 0.9082   |
| 0.6597        | 25.0  | 225  | 0.4221          | 0.9072   |
| 0.6146        | 26.0  | 234  | 0.4013          | 0.9166   |
| 0.6162        | 27.0  | 243  | 0.3853          | 0.9119   |
| 0.6252        | 28.0  | 252  | 0.3886          | 0.9100   |
| 0.5666        | 29.0  | 261  | 0.3478          | 0.9269   |
| 0.5698        | 30.0  | 270  | 0.3489          | 0.9250   |
| 0.5575        | 31.0  | 279  | 0.3354          | 0.9260   |
| 0.5298        | 32.0  | 288  | 0.3299          | 0.9203   |
| 0.5267        | 33.0  | 297  | 0.3128          | 0.9297   |
| 0.5558        | 34.0  | 306  | 0.3070          | 0.9316   |
| 0.5541        | 35.0  | 315  | 0.3005          | 0.9335   |
| 0.5328        | 36.0  | 324  | 0.2908          | 0.9363   |
| 0.5566        | 37.0  | 333  | 0.2923          | 0.9325   |
| 0.5184        | 38.0  | 342  | 0.2825          | 0.9363   |
| 0.4649        | 39.0  | 351  | 0.2739          | 0.9391   |
| 0.431         | 40.0  | 360  | 0.2698          | 0.9335   |
| 0.4681        | 41.0  | 369  | 0.2643          | 0.9372   |
| 0.4918        | 42.0  | 378  | 0.2611          | 0.9372   |
| 0.4688        | 43.0  | 387  | 0.2608          | 0.9381   |
| 0.4738        | 44.0  | 396  | 0.2621          | 0.9372   |
| 0.4669        | 45.0  | 405  | 0.2604          | 0.9381   |
| 0.4556        | 46.0  | 414  | 0.2596          | 0.9344   |
| 0.4498        | 47.0  | 423  | 0.2564          | 0.9400   |
| 0.4738        | 48.0  | 432  | 0.2564          | 0.9400   |
| 0.4494        | 49.0  | 441  | 0.2564          | 0.9391   |
| 0.447         | 50.0  | 450  | 0.2564          | 0.9391   |


### Framework versions

- Transformers 4.35.2
- Pytorch 1.12.1+cu116
- Datasets 2.15.0
- Tokenizers 0.15.2