Commit
·
008aa31
1
Parent(s):
405b165
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: psst_batch_size_4_base_model
|
| 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 |
+
# psst_batch_size_4_base_model
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.6743
|
| 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: 4
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 8
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 100
|
| 45 |
+
- num_epochs: 30
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 14.1952 | 1.68 | 100 | 3.6352 |
|
| 52 |
+
| 3.9092 | 3.36 | 200 | 3.7223 |
|
| 53 |
+
| 3.9981 | 5.04 | 300 | 3.6864 |
|
| 54 |
+
| 3.7209 | 6.72 | 400 | 3.6310 |
|
| 55 |
+
| 3.9395 | 8.4 | 500 | 3.7229 |
|
| 56 |
+
| 3.7126 | 10.08 | 600 | 3.6163 |
|
| 57 |
+
| 3.6999 | 11.76 | 700 | 3.6776 |
|
| 58 |
+
| 3.7203 | 13.45 | 800 | 3.7568 |
|
| 59 |
+
| 3.7202 | 15.13 | 900 | 3.6998 |
|
| 60 |
+
| 3.7023 | 16.81 | 1000 | 3.6943 |
|
| 61 |
+
| 3.689 | 18.49 | 1100 | 3.6501 |
|
| 62 |
+
| 3.7009 | 20.17 | 1200 | 3.6973 |
|
| 63 |
+
| 3.6882 | 21.85 | 1300 | 3.6938 |
|
| 64 |
+
| 3.6907 | 23.53 | 1400 | 3.6795 |
|
| 65 |
+
| 3.6869 | 25.21 | 1500 | 3.6727 |
|
| 66 |
+
| 3.681 | 26.89 | 1600 | 3.6749 |
|
| 67 |
+
| 3.6968 | 28.57 | 1700 | 3.6743 |
|
| 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
|