jstoone commited on
Commit
157ff51
1 Parent(s): a629aae

End of training

Browse files
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bookbot/distil-ast-audioset
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - Nooon/Donate_a_cry
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distil-ast-audioset-finetuned-cry
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: DonateACry
18
+ type: Nooon/Donate_a_cry
19
+ config: train
20
+ split: train
21
+ args: train
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9347826086956522
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # distil-ast-audioset-finetuned-cry
32
+
33
+ This model is a fine-tuned version of [bookbot/distil-ast-audioset](https://huggingface.co/bookbot/distil-ast-audioset) on the DonateACry dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2731
36
+ - Accuracy: 0.9348
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.05
62
+ - num_epochs: 10
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.424 | 1.0 | 46 | 0.2375 | 0.9565 |
70
+ | 0.5755 | 2.0 | 92 | 0.3218 | 0.9565 |
71
+ | 0.5466 | 3.0 | 138 | 0.1731 | 0.9565 |
72
+ | 0.3545 | 4.0 | 184 | 0.2719 | 0.9348 |
73
+ | 0.0759 | 5.0 | 230 | 0.1582 | 0.9348 |
74
+ | 0.0178 | 6.0 | 276 | 0.2576 | 0.9130 |
75
+ | 0.0032 | 7.0 | 322 | 0.2695 | 0.9348 |
76
+ | 0.0014 | 8.0 | 368 | 0.2496 | 0.9348 |
77
+ | 0.0005 | 9.0 | 414 | 0.2639 | 0.9348 |
78
+ | 0.0004 | 10.0 | 460 | 0.2731 | 0.9348 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.35.0
84
+ - Pytorch 2.1.0+cu118
85
+ - Datasets 2.14.6
86
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bookbot/distil-ast-audioset",
3
+ "architectures": [
4
+ "ASTForAudioClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "frequency_stride": 10,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "belly_pain",
13
+ "1": "burping",
14
+ "2": "discomfort",
15
+ "3": "hungry",
16
+ "4": "tired"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "belly_pain": "0",
22
+ "burping": "1",
23
+ "discomfort": "2",
24
+ "hungry": "3",
25
+ "tired": "4"
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_length": 1024,
29
+ "model_type": "audio-spectrogram-transformer",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 6,
32
+ "num_mel_bins": 128,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "time_stride": 10,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.35.0"
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2d161e21e908a7f06612e95275e6b070f76b3ee3f1d23840321884dabc2935
3
+ size 174676564
preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "ASTFeatureExtractor",
4
+ "feature_size": 1,
5
+ "max_length": 1024,
6
+ "mean": -4.2677393,
7
+ "num_mel_bins": 128,
8
+ "padding_side": "right",
9
+ "padding_value": 0.0,
10
+ "return_attention_mask": false,
11
+ "sampling_rate": 16000,
12
+ "std": 4.5689974
13
+ }
runs/Nov05_13-23-46_501c447c709e/events.out.tfevents.1699190643.501c447c709e.8788.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cb82eb15be7afbb89dc27b714496b362f35b30394441653b27d5224fcbea1c
3
+ size 22418
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1677aac76d77dda3be46cdbffeb770ed9a24930e828a63b2774e84d3d7436f
3
+ size 4600