End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-medium
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: MAScIR_elderly_whisper-medium-LoRA-for_test
|
| 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 |
+
# MAScIR_elderly_whisper-medium-LoRA-for_test
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0403
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.001
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 200
|
| 44 |
+
- num_epochs: 3
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 0.2935 | 0.19 | 100 | 0.2595 |
|
| 51 |
+
| 0.3101 | 0.38 | 200 | 0.2421 |
|
| 52 |
+
| 0.2404 | 0.57 | 300 | 0.2664 |
|
| 53 |
+
| 0.2303 | 0.76 | 400 | 0.2072 |
|
| 54 |
+
| 0.2021 | 0.95 | 500 | 0.1893 |
|
| 55 |
+
| 0.1075 | 1.14 | 600 | 0.1650 |
|
| 56 |
+
| 0.1222 | 1.33 | 700 | 0.1328 |
|
| 57 |
+
| 0.1036 | 1.52 | 800 | 0.1077 |
|
| 58 |
+
| 0.0908 | 1.71 | 900 | 0.0835 |
|
| 59 |
+
| 0.0701 | 1.9 | 1000 | 0.0727 |
|
| 60 |
+
| 0.029 | 2.09 | 1100 | 0.0587 |
|
| 61 |
+
| 0.0264 | 2.28 | 1200 | 0.0522 |
|
| 62 |
+
| 0.0164 | 2.47 | 1300 | 0.0507 |
|
| 63 |
+
| 0.0162 | 2.66 | 1400 | 0.0459 |
|
| 64 |
+
| 0.0151 | 2.85 | 1500 | 0.0403 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.35.0.dev0
|
| 70 |
+
- Pytorch 2.0.1+cu118
|
| 71 |
+
- Datasets 2.14.5
|
| 72 |
+
- Tokenizers 0.14.0
|