Commit
·
b702020
1
Parent(s):
844e381
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-base-intent-classification-ori
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-base-intent-classification-ori
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6860
|
| 20 |
+
- Accuracy: 0.7917
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 8
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 45
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 2.1955 | 1.0 | 14 | 2.1826 | 0.25 |
|
| 55 |
+
| 2.1863 | 2.0 | 28 | 2.1211 | 0.3333 |
|
| 56 |
+
| 2.1137 | 3.0 | 42 | 2.0599 | 0.3333 |
|
| 57 |
+
| 2.0855 | 4.0 | 56 | 2.0110 | 0.3333 |
|
| 58 |
+
| 2.02 | 5.0 | 70 | 1.8870 | 0.3958 |
|
| 59 |
+
| 1.9762 | 6.0 | 84 | 1.7885 | 0.4375 |
|
| 60 |
+
| 1.8745 | 7.0 | 98 | 1.7575 | 0.4583 |
|
| 61 |
+
| 1.7797 | 8.0 | 112 | 1.7475 | 0.4375 |
|
| 62 |
+
| 1.7613 | 9.0 | 126 | 1.4668 | 0.5417 |
|
| 63 |
+
| 1.5637 | 10.0 | 140 | 1.3769 | 0.4583 |
|
| 64 |
+
| 1.4365 | 11.0 | 154 | 1.4320 | 0.4792 |
|
| 65 |
+
| 1.4563 | 12.0 | 168 | 1.3770 | 0.5 |
|
| 66 |
+
| 1.2626 | 13.0 | 182 | 1.2775 | 0.5208 |
|
| 67 |
+
| 1.2228 | 14.0 | 196 | 1.3321 | 0.4792 |
|
| 68 |
+
| 1.14 | 15.0 | 210 | 1.1823 | 0.5417 |
|
| 69 |
+
| 1.0518 | 16.0 | 224 | 1.2527 | 0.4792 |
|
| 70 |
+
| 1.1248 | 17.0 | 238 | 1.0706 | 0.625 |
|
| 71 |
+
| 0.917 | 18.0 | 252 | 1.0176 | 0.6042 |
|
| 72 |
+
| 0.8725 | 19.0 | 266 | 1.0971 | 0.5833 |
|
| 73 |
+
| 0.7962 | 20.0 | 280 | 0.9867 | 0.6042 |
|
| 74 |
+
| 0.7203 | 21.0 | 294 | 0.8614 | 0.6667 |
|
| 75 |
+
| 0.5947 | 22.0 | 308 | 0.8979 | 0.6875 |
|
| 76 |
+
| 0.5722 | 23.0 | 322 | 0.8487 | 0.6667 |
|
| 77 |
+
| 0.5088 | 24.0 | 336 | 0.8713 | 0.625 |
|
| 78 |
+
| 0.4422 | 25.0 | 350 | 0.6776 | 0.8333 |
|
| 79 |
+
| 0.4164 | 26.0 | 364 | 0.6572 | 0.8125 |
|
| 80 |
+
| 0.3846 | 27.0 | 378 | 0.7982 | 0.7083 |
|
| 81 |
+
| 0.331 | 28.0 | 392 | 0.7706 | 0.7708 |
|
| 82 |
+
| 0.2883 | 29.0 | 406 | 0.7989 | 0.6875 |
|
| 83 |
+
| 0.2318 | 30.0 | 420 | 0.5795 | 0.8125 |
|
| 84 |
+
| 0.2155 | 31.0 | 434 | 0.6404 | 0.8125 |
|
| 85 |
+
| 0.2071 | 32.0 | 448 | 0.7110 | 0.7708 |
|
| 86 |
+
| 0.1691 | 33.0 | 462 | 0.7089 | 0.7917 |
|
| 87 |
+
| 0.1676 | 34.0 | 476 | 0.6462 | 0.8125 |
|
| 88 |
+
| 0.1418 | 35.0 | 490 | 0.6559 | 0.8125 |
|
| 89 |
+
| 0.1324 | 36.0 | 504 | 0.6449 | 0.8125 |
|
| 90 |
+
| 0.1503 | 37.0 | 518 | 0.6334 | 0.8125 |
|
| 91 |
+
| 0.1193 | 38.0 | 532 | 0.6347 | 0.8125 |
|
| 92 |
+
| 0.123 | 39.0 | 546 | 0.6336 | 0.8125 |
|
| 93 |
+
| 0.1109 | 40.0 | 560 | 0.6892 | 0.7917 |
|
| 94 |
+
| 0.1025 | 41.0 | 574 | 0.7381 | 0.7708 |
|
| 95 |
+
| 0.1122 | 42.0 | 588 | 0.7132 | 0.7917 |
|
| 96 |
+
| 0.1041 | 43.0 | 602 | 0.6976 | 0.7917 |
|
| 97 |
+
| 0.1074 | 44.0 | 616 | 0.6883 | 0.7917 |
|
| 98 |
+
| 0.102 | 45.0 | 630 | 0.6860 | 0.7917 |
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
### Framework versions
|
| 102 |
+
|
| 103 |
+
- Transformers 4.20.1
|
| 104 |
+
- Pytorch 1.11.0
|
| 105 |
+
- Datasets 2.1.0
|
| 106 |
+
- Tokenizers 0.12.1
|