update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_truncated
|
| 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_truncated
|
| 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: 1.3514
|
| 22 |
+
- Accuracy: 0.7236
|
| 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: 2000
|
| 53 |
+
- num_epochs: 5.0
|
| 54 |
+
- mixed_precision_training: Native AMP
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 59 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 60 |
+
| 0.5296 | 0.26 | 1000 | 2.6633 | 0.4016 |
|
| 61 |
+
| 0.4252 | 0.52 | 2000 | 1.8582 | 0.5751 |
|
| 62 |
+
| 0.2989 | 0.78 | 3000 | 1.6780 | 0.6332 |
|
| 63 |
+
| 0.3563 | 1.04 | 4000 | 1.4479 | 0.6799 |
|
| 64 |
+
| 0.1617 | 1.3 | 5000 | 1.5066 | 0.6679 |
|
| 65 |
+
| 0.1409 | 1.56 | 6000 | 1.4082 | 0.6992 |
|
| 66 |
+
| 0.01 | 1.82 | 7000 | 1.2448 | 0.7071 |
|
| 67 |
+
| 0.0018 | 2.08 | 8000 | 1.1996 | 0.7148 |
|
| 68 |
+
| 0.0014 | 2.34 | 9000 | 1.6505 | 0.6410 |
|
| 69 |
+
| 0.0188 | 2.6 | 10000 | 1.4050 | 0.6840 |
|
| 70 |
+
| 0.0007 | 2.86 | 11000 | 1.5831 | 0.6621 |
|
| 71 |
+
| 0.1038 | 3.12 | 12000 | 1.5441 | 0.6829 |
|
| 72 |
+
| 0.0003 | 3.38 | 13000 | 1.3483 | 0.6900 |
|
| 73 |
+
| 0.0004 | 3.64 | 14000 | 1.7070 | 0.6414 |
|
| 74 |
+
| 0.0003 | 3.9 | 15000 | 1.3198 | 0.7075 |
|
| 75 |
+
| 0.0002 | 4.16 | 16000 | 1.3118 | 0.7105 |
|
| 76 |
+
| 0.0001 | 4.42 | 17000 | 1.4099 | 0.7029 |
|
| 77 |
+
| 0.0 | 4.68 | 18000 | 1.3658 | 0.7180 |
|
| 78 |
+
| 0.0001 | 4.93 | 19000 | 1.3514 | 0.7236 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.18.0.dev0
|
| 84 |
+
- Pytorch 1.11.0+cu113
|
| 85 |
+
- Datasets 1.18.4.dev0
|
| 86 |
+
- Tokenizers 0.11.6
|