update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- wer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: libri-alpha-0.75-Temp-1-attention-3-layers-distil-with-6-layers-mse-take-3
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# libri-alpha-0.75-Temp-1-attention-3-layers-distil-with-6-layers-mse-take-3
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [rohitp1/libri-alpha-0.75-Temp-1-attention-3-layers-distil-with-6-layers-mse](https://huggingface.co/rohitp1/libri-alpha-0.75-Temp-1-attention-3-layers-distil-with-6-layers-mse) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 28.9263
|
| 19 |
+
- Wer: 0.3301
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0005
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 47 |
+
- num_epochs: 40
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 291.1088 | 0.22 | 400 | 28.4207 | 0.3362 |
|
| 55 |
+
| 284.1968 | 0.45 | 800 | 28.1458 | 0.3314 |
|
| 56 |
+
| 288.1414 | 0.67 | 1200 | 28.1397 | 0.3326 |
|
| 57 |
+
| 290.0272 | 0.9 | 1600 | 28.4186 | 0.3323 |
|
| 58 |
+
| 287.3224 | 1.12 | 2000 | 28.3548 | 0.3283 |
|
| 59 |
+
| 279.1482 | 1.35 | 2400 | 28.5373 | 0.3309 |
|
| 60 |
+
| 285.8217 | 1.57 | 2800 | 28.4447 | 0.3301 |
|
| 61 |
+
| 282.9265 | 1.79 | 3200 | 28.5379 | 0.3365 |
|
| 62 |
+
| 292.6254 | 2.02 | 3600 | 28.2632 | 0.3299 |
|
| 63 |
+
| 279.215 | 2.24 | 4000 | 28.9263 | 0.3301 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.24.0
|
| 69 |
+
- Pytorch 1.12.1
|
| 70 |
+
- Datasets 2.7.1
|
| 71 |
+
- Tokenizers 0.11.0
|