updated epoch 3
Browse files
README.md
CHANGED
@@ -37,8 +37,6 @@ language:
|
|
37 |
- ja
|
38 |
pipeline_tag: audio-classification
|
39 |
---
|
40 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
-
should probably proofread and complete it, then remove this comment. -->
|
42 |
|
43 |
# WAV2VEC2_CAPSTONE_MODEL
|
44 |
|
@@ -57,22 +55,22 @@ More information needed
|
|
57 |
### Training hyperparameters
|
58 |
The following hyperparameters were used during training:
|
59 |
- learning_rate: 0.0003
|
60 |
-
- train_batch_size:
|
61 |
-
- eval_batch_size:
|
62 |
- seed: 42
|
63 |
-
- gradient_accumulation_steps:
|
64 |
-
- total_train_batch_size:
|
65 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
66 |
- lr_scheduler_type: linear
|
67 |
- lr_scheduler_warmup_ratio: 0.1
|
68 |
-
- num_epochs:
|
69 |
- mixed_precision_training: Native AMP
|
70 |
### Training results
|
71 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 score |
|
72 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
73 |
| 0.9339 | 1.0 | 776 | 1.4214 | 0.7162 | 0.7094 |
|
74 |
| 0.5663 | 2.0 | 1552 | 1.0182 | 0.8318 | 0.8277 |
|
75 |
-
| 0.
|
76 |
| 0.4882 | 4.0 | 2055 | 0.5092 | 0.8474 | 0.8478 |
|
77 |
| 0.2305 | 5.0 | 2569 | 0.5244 | 0.8643 | 0.8639 |
|
78 |
| 0.1219 | 6.0 | 3082 | 0.4169 | 0.8966 | 0.8966 |
|
|
|
37 |
- ja
|
38 |
pipeline_tag: audio-classification
|
39 |
---
|
|
|
|
|
40 |
|
41 |
# WAV2VEC2_CAPSTONE_MODEL
|
42 |
|
|
|
55 |
### Training hyperparameters
|
56 |
The following hyperparameters were used during training:
|
57 |
- learning_rate: 0.0003
|
58 |
+
- train_batch_size: 8
|
59 |
+
- eval_batch_size: 8
|
60 |
- seed: 42
|
61 |
+
- gradient_accumulation_steps: 10
|
62 |
+
- total_train_batch_size: 80
|
63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
- lr_scheduler_type: linear
|
65 |
- lr_scheduler_warmup_ratio: 0.1
|
66 |
+
- num_epochs: 8
|
67 |
- mixed_precision_training: Native AMP
|
68 |
### Training results
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 score |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
71 |
| 0.9339 | 1.0 | 776 | 1.4214 | 0.7162 | 0.7094 |
|
72 |
| 0.5663 | 2.0 | 1552 | 1.0182 | 0.8318 | 0.8277 |
|
73 |
+
| 0.4408 | 3.0 | 2328 | 0.6117 | 0.8795 | 0.8784 |
|
74 |
| 0.4882 | 4.0 | 2055 | 0.5092 | 0.8474 | 0.8478 |
|
75 |
| 0.2305 | 5.0 | 2569 | 0.5244 | 0.8643 | 0.8639 |
|
76 |
| 0.1219 | 6.0 | 3082 | 0.4169 | 0.8966 | 0.8966 |
|