Marcos12886 commited on
Commit
657506f
1 Parent(s): 805a9df

End of training

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: ntu-spml/distilhubert
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - audiofolder
8
+ model-index:
9
+ - name: distilhubert-finetuned-cry-detector
10
+ results: []
11
+ ---
12
+
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
+ # distilhubert-finetuned-cry-detector
17
+
18
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
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: 0.0001
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 123
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - num_epochs: 1
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
51
+ | No log | 0.9888 | 11 | 1.6532 | 0.5506 |
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.42.3
57
+ - Pytorch 2.3.1+cu118
58
+ - Datasets 2.20.0
59
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 768,
51
+ "id2label": {
52
+ "0": "Baby laugh",
53
+ "1": "Crying baby",
54
+ "2": "Noise",
55
+ "3": "Silence",
56
+ "4": "belly_pain",
57
+ "5": "burping",
58
+ "6": "discomfort",
59
+ "7": "hungry",
60
+ "8": "tired"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "Baby laugh": "0",
66
+ "Crying baby": "1",
67
+ "Noise": "2",
68
+ "Silence": "3",
69
+ "belly_pain": "4",
70
+ "burping": "5",
71
+ "discomfort": "6",
72
+ "hungry": "7",
73
+ "tired": "8"
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "layerdrop": 0.0,
77
+ "mask_feature_length": 10,
78
+ "mask_feature_min_masks": 0,
79
+ "mask_feature_prob": 0.0,
80
+ "mask_time_length": 10,
81
+ "mask_time_min_masks": 2,
82
+ "mask_time_prob": 0.05,
83
+ "model_type": "hubert",
84
+ "num_attention_heads": 12,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 2,
89
+ "pad_token_id": 0,
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.42.3",
92
+ "use_weighted_layer_sum": false,
93
+ "vocab_size": 32
94
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20a9c6637a79559507b479b402d7acbb1f95f20c0502d6e6ff4fa53fc3ca03f
3
+ size 94770700
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
runs/Jul17_20-31-13_DesMar/events.out.tfevents.1721241074.DesMar.6308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1457432d39a7163f571dee75b4f4e1cb4b1351a959cc38a91ed916a688f1fe
3
+ size 6790
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992fe29adba7f9bad40307dcb16fe956948e2e21ea6cb4af3cf294b11bf789d2
3
+ size 5176