update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- xtreme_s
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: xtreme_s_xlsr_300m_minds14_resplit
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# xtreme_s_xlsr_300m_minds14_resplit
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the xtreme_s dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3826
|
| 23 |
+
- F1: 0.9106
|
| 24 |
+
- Accuracy: 0.9103
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0003
|
| 44 |
+
- train_batch_size: 32
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- distributed_type: multi-GPU
|
| 48 |
+
- num_devices: 2
|
| 49 |
+
- total_train_batch_size: 64
|
| 50 |
+
- total_eval_batch_size: 16
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: linear
|
| 53 |
+
- lr_scheduler_warmup_steps: 1500
|
| 54 |
+
- num_epochs: 50.0
|
| 55 |
+
- mixed_precision_training: Native AMP
|
| 56 |
+
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|
| 60 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
|
| 61 |
+
| 2.6739 | 5.41 | 200 | 2.5687 | 0.0430 | 0.1190 |
|
| 62 |
+
| 1.4953 | 10.81 | 400 | 1.6052 | 0.5550 | 0.5692 |
|
| 63 |
+
| 0.6177 | 16.22 | 600 | 0.7927 | 0.8052 | 0.8011 |
|
| 64 |
+
| 0.3609 | 21.62 | 800 | 0.5679 | 0.8609 | 0.8609 |
|
| 65 |
+
| 0.4972 | 27.03 | 1000 | 0.5944 | 0.8509 | 0.8523 |
|
| 66 |
+
| 0.1799 | 32.43 | 1200 | 0.6194 | 0.8623 | 0.8621 |
|
| 67 |
+
| 0.1308 | 37.84 | 1400 | 0.5956 | 0.8569 | 0.8548 |
|
| 68 |
+
| 0.2298 | 43.24 | 1600 | 0.5201 | 0.8732 | 0.8743 |
|
| 69 |
+
| 0.0052 | 48.65 | 1800 | 0.3826 | 0.9106 | 0.9103 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.18.0.dev0
|
| 75 |
+
- Pytorch 1.10.2+cu113
|
| 76 |
+
- Datasets 2.0.1.dev0
|
| 77 |
+
- Tokenizers 0.11.6
|