End of training
Browse files
README.md
CHANGED
|
@@ -13,13 +13,28 @@ model-index:
|
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/khackho01125-CMC-University/huggingface/runs/
|
|
|
|
| 17 |
# test-model
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
### Training hyperparameters
|
| 25 |
|
|
@@ -33,23 +48,23 @@ The following hyperparameters were used during training:
|
|
| 33 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 34 |
- lr_scheduler_type: linear
|
| 35 |
- lr_scheduler_warmup_ratio: 0.3
|
| 36 |
-
-
|
| 37 |
- mixed_precision_training: Native AMP
|
| 38 |
|
| 39 |
### Training results
|
| 40 |
|
| 41 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 42 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 43 |
-
| 1.
|
| 44 |
-
| 0.
|
| 45 |
-
| 0.
|
| 46 |
-
| 0.
|
| 47 |
-
| 0.
|
| 48 |
-
| 0.463 | 5.
|
| 49 |
-
| 0.
|
| 50 |
-
| 0.
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/khackho01125-CMC-University/huggingface/runs/v98t7due)
|
| 17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/khackho01125-CMC-University/huggingface/runs/v98t7due)
|
| 18 |
# test-model
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3880
|
| 23 |
+
- Accuracy: 0.8994
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
|
| 39 |
### Training hyperparameters
|
| 40 |
|
|
|
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_ratio: 0.3
|
| 51 |
+
- training_steps: 600
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 58 |
+
| 1.0477 | 0.9639 | 60 | 0.9638 | 0.5412 |
|
| 59 |
+
| 0.9116 | 1.9277 | 120 | 0.7981 | 0.7123 |
|
| 60 |
+
| 0.76 | 2.8916 | 180 | 0.6920 | 0.7425 |
|
| 61 |
+
| 0.6584 | 3.8554 | 240 | 0.5988 | 0.7666 |
|
| 62 |
+
| 0.5391 | 4.8193 | 300 | 0.5216 | 0.8471 |
|
| 63 |
+
| 0.463 | 5.7831 | 360 | 0.4832 | 0.8551 |
|
| 64 |
+
| 0.3977 | 6.7470 | 420 | 0.4274 | 0.8833 |
|
| 65 |
+
| 0.3647 | 7.7108 | 480 | 0.4347 | 0.8753 |
|
| 66 |
+
| 0.33 | 8.6747 | 540 | 0.3900 | 0.8833 |
|
| 67 |
+
| 0.318 | 9.6386 | 600 | 0.3880 | 0.8994 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|