|
--- |
|
language: |
|
- en-US |
|
license: apache-2.0 |
|
tags: |
|
- minds14 |
|
- google/xtreme_s |
|
- generated_from_trainer |
|
datasets: |
|
- xtreme_s |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xtreme_s_xlsr_300m_mt5-small_minds14.en-US |
|
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. --> |
|
|
|
# xtreme_s_xlsr_300m_mt5-small_minds14.en-US |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the GOOGLE/XTREME_S - MINDS14.EN-US dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.7321 |
|
- F1: 0.0154 |
|
- Accuracy: 0.0638 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 64 |
|
- 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: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 50.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| 2.6067 | 3.95 | 20 | 2.6501 | 0.0112 | 0.0851 | |
|
| 2.5614 | 7.95 | 40 | 2.8018 | 0.0133 | 0.0603 | |
|
| 2.2836 | 11.95 | 60 | 3.0786 | 0.0084 | 0.0603 | |
|
| 1.9597 | 15.95 | 80 | 3.2288 | 0.0126 | 0.0638 | |
|
| 1.5566 | 19.95 | 100 | 3.6934 | 0.0178 | 0.0567 | |
|
| 1.3168 | 23.95 | 120 | 3.9135 | 0.0150 | 0.0638 | |
|
| 1.0598 | 27.95 | 140 | 4.2618 | 0.0084 | 0.0603 | |
|
| 0.5721 | 31.95 | 160 | 3.7973 | 0.0354 | 0.0780 | |
|
| 0.4402 | 35.95 | 180 | 4.6233 | 0.0179 | 0.0638 | |
|
| 0.6113 | 39.95 | 200 | 4.6149 | 0.0208 | 0.0674 | |
|
| 0.3938 | 43.95 | 220 | 4.7886 | 0.0159 | 0.0638 | |
|
| 0.2473 | 47.95 | 240 | 4.7321 | 0.0154 | 0.0638 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|
