Commit
·
bbd7cd9
1
Parent(s):
f13c5a8
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: batch_size_2
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# batch_size_2
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.8600
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0003
|
| 37 |
+
- train_batch_size: 2
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 4
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 200
|
| 45 |
+
- num_epochs: 30
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 13.2945 | 1.69 | 200 | 3.6357 |
|
| 52 |
+
| 3.737 | 3.38 | 400 | 3.6624 |
|
| 53 |
+
| 3.707 | 5.06 | 600 | 3.6271 |
|
| 54 |
+
| 3.6038 | 6.75 | 800 | 3.5749 |
|
| 55 |
+
| 3.4502 | 8.44 | 1000 | 3.2693 |
|
| 56 |
+
| 3.1641 | 10.13 | 1200 | 2.9155 |
|
| 57 |
+
| 2.6047 | 11.81 | 1400 | 2.3544 |
|
| 58 |
+
| 2.0028 | 13.5 | 1600 | 2.0022 |
|
| 59 |
+
| 1.5415 | 15.19 | 1800 | 1.8024 |
|
| 60 |
+
| 1.1696 | 16.88 | 2000 | 1.7754 |
|
| 61 |
+
| 0.8809 | 18.57 | 2200 | 1.6793 |
|
| 62 |
+
| 0.7591 | 20.25 | 2400 | 1.8127 |
|
| 63 |
+
| 0.6056 | 21.94 | 2600 | 1.7993 |
|
| 64 |
+
| 0.5091 | 23.63 | 2800 | 1.7812 |
|
| 65 |
+
| 0.4569 | 25.32 | 3000 | 1.7781 |
|
| 66 |
+
| 0.4167 | 27.0 | 3200 | 1.8802 |
|
| 67 |
+
| 0.3432 | 28.69 | 3400 | 1.8600 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.28.0
|
| 73 |
+
- Pytorch 2.0.1
|
| 74 |
+
- Datasets 2.12.0
|
| 75 |
+
- Tokenizers 0.13.2
|