update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- xtreme_s
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: xtreme_s_xlsr_300m_fleurs_langid_quicker_warmup
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# xtreme_s_xlsr_300m_fleurs_langid_quicker_warmup
|
| 18 |
+
|
| 19 |
+
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.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.9765
|
| 22 |
+
- Accuracy: 0.6199
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 8
|
| 47 |
+
- gradient_accumulation_steps: 2
|
| 48 |
+
- total_train_batch_size: 64
|
| 49 |
+
- total_eval_batch_size: 8
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_steps: 1000
|
| 53 |
+
- num_epochs: 10.0
|
| 54 |
+
- mixed_precision_training: Native AMP
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
|
| 60 |
+
| 0.6644 | 0.26 | 1000 | 0.3071 | 3.2482 |
|
| 61 |
+
| 0.394 | 0.52 | 2000 | 0.5948 | 1.8833 |
|
| 62 |
+
| 0.1034 | 0.78 | 3000 | 0.6297 | 1.5852 |
|
| 63 |
+
| 0.1088 | 1.04 | 4000 | 0.5992 | 1.7903 |
|
| 64 |
+
| 0.0032 | 1.3 | 5000 | 0.6356 | 1.6219 |
|
| 65 |
+
| 0.1813 | 1.56 | 6000 | 0.5788 | 1.8168 |
|
| 66 |
+
| 0.0654 | 1.82 | 7000 | 0.6234 | 1.6089 |
|
| 67 |
+
| 0.0144 | 2.08 | 8000 | 0.6424 | 1.6071 |
|
| 68 |
+
| 0.0019 | 2.34 | 9000 | 0.5822 | 1.7820 |
|
| 69 |
+
| 0.0159 | 2.6 | 10000 | 0.6043 | 1.8407 |
|
| 70 |
+
| 0.0029 | 2.86 | 11000 | 0.5845 | 1.8600 |
|
| 71 |
+
| 0.0458 | 3.12 | 12000 | 0.6299 | 1.6591 |
|
| 72 |
+
| 0.013 | 3.38 | 13000 | 0.5903 | 2.0788 |
|
| 73 |
+
| 0.003 | 3.64 | 14000 | 0.6188 | 1.7645 |
|
| 74 |
+
| 0.0015 | 3.9 | 15000 | 0.6328 | 1.7739 |
|
| 75 |
+
| 0.0003 | 4.16 | 16000 | 0.6072 | 1.8742 |
|
| 76 |
+
| 0.0005 | 4.42 | 17000 | 0.6231 | 1.7102 |
|
| 77 |
+
| 0.006 | 4.68 | 18000 | 0.6122 | 1.6909 |
|
| 78 |
+
| 0.2367 | 4.93 | 19000 | 0.6029 | 1.9891 |
|
| 79 |
+
| 0.005 | 5.19 | 20000 | 0.6220 | 1.7245 |
|
| 80 |
+
| 0.0813 | 5.45 | 21000 | 0.5739 | 2.0495 |
|
| 81 |
+
| 0.1233 | 5.71 | 22000 | 0.6104 | 1.9601 |
|
| 82 |
+
| 0.0003 | 5.97 | 23000 | 0.5924 | 1.8881 |
|
| 83 |
+
| 0.0003 | 6.23 | 24000 | 0.6055 | 1.9568 |
|
| 84 |
+
| 0.0001 | 6.49 | 25000 | 0.6086 | 1.8489 |
|
| 85 |
+
| 0.2198 | 6.75 | 26000 | 0.6292 | 1.8048 |
|
| 86 |
+
| 0.0261 | 7.01 | 27000 | 2.0284 | 0.5989 |
|
| 87 |
+
| 0.0001 | 7.27 | 28000 | 1.7323 | 0.6431 |
|
| 88 |
+
| 0.0001 | 7.53 | 29000 | 1.9329 | 0.6310 |
|
| 89 |
+
| 0.0011 | 7.79 | 30000 | 1.9256 | 0.6107 |
|
| 90 |
+
| 0.0933 | 8.05 | 31000 | 2.3915 | 0.5896 |
|
| 91 |
+
| 0.0001 | 8.31 | 32000 | 1.9948 | 0.6021 |
|
| 92 |
+
| 0.0003 | 8.57 | 33000 | 1.9518 | 0.6126 |
|
| 93 |
+
| 0.0005 | 8.83 | 34000 | 1.8935 | 0.6243 |
|
| 94 |
+
| 0.0 | 9.09 | 35000 | 2.0177 | 0.6144 |
|
| 95 |
+
| 0.0002 | 9.35 | 36000 | 2.0234 | 0.6174 |
|
| 96 |
+
| 0.0 | 9.61 | 37000 | 1.9568 | 0.6216 |
|
| 97 |
+
| 0.0 | 9.87 | 38000 | 1.9765 | 0.6199 |
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
### Framework versions
|
| 101 |
+
|
| 102 |
+
- Transformers 4.18.0.dev0
|
| 103 |
+
- Pytorch 1.11.0+cu113
|
| 104 |
+
- Datasets 1.18.4.dev0
|
| 105 |
+
- Tokenizers 0.11.6
|