End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/hubert-base-ls960
|
| 4 |
+
tags:
|
| 5 |
+
- audio-classification
|
| 6 |
+
- hubert
|
| 7 |
+
- esc50
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: hubert-esc50-finetuned
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# hubert-esc50-finetuned
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the ESC-50 dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.3860
|
| 24 |
+
- Accuracy: 0.3625
|
| 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: 5e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 3.7931 | 1.0 | 200 | 3.7608 | 0.0275 |
|
| 56 |
+
| 3.6397 | 2.0 | 400 | 3.5743 | 0.065 |
|
| 57 |
+
| 3.3959 | 3.0 | 600 | 3.3550 | 0.0975 |
|
| 58 |
+
| 3.2348 | 4.0 | 800 | 3.1394 | 0.1375 |
|
| 59 |
+
| 2.9701 | 5.0 | 1000 | 2.9271 | 0.2175 |
|
| 60 |
+
| 2.9462 | 6.0 | 1200 | 2.7442 | 0.23 |
|
| 61 |
+
| 2.728 | 7.0 | 1400 | 2.6029 | 0.275 |
|
| 62 |
+
| 2.5537 | 8.0 | 1600 | 2.4791 | 0.3125 |
|
| 63 |
+
| 2.4586 | 9.0 | 1800 | 2.4028 | 0.35 |
|
| 64 |
+
| 2.3136 | 10.0 | 2000 | 2.3860 | 0.3625 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.37.2
|
| 70 |
+
- Pytorch 2.0.1+cu117
|
| 71 |
+
- Datasets 2.16.1
|
| 72 |
+
- Tokenizers 0.15.1
|