Marcos12886 commited on
Commit
5633f20
1 Parent(s): f46a366

End of training

Browse files
Files changed (5) hide show
  1. README.md +78 -78
  2. config.json +86 -86
  3. model.safetensors +1 -1
  4. preprocessor_config.json +9 -9
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,78 +1,78 @@
1
- ---
2
- license: apache-2.0
3
- base_model: ntu-spml/distilhubert
4
- tags:
5
- - generated_from_trainer
6
- datasets:
7
- - audiofolder
8
- metrics:
9
- - accuracy
10
- model-index:
11
- - name: distilhubert-finetuned-donateacry
12
- results:
13
- - task:
14
- name: Audio Classification
15
- type: audio-classification
16
- dataset:
17
- name: audiofolder
18
- type: audiofolder
19
- config: default
20
- split: train
21
- args: default
22
- metrics:
23
- - name: Accuracy
24
- type: accuracy
25
- value: 0.8369565217391305
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
- # distilhubert-finetuned-donateacry
32
-
33
- This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
34
- It achieves the following results on the evaluation set:
35
- - Loss: 0.6684
36
- - Accuracy: 0.8370
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: 0.0005
56
- - train_batch_size: 8
57
- - eval_batch_size: 8
58
- - seed: 123
59
- - gradient_accumulation_steps: 8
60
- - total_train_batch_size: 64
61
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
- - lr_scheduler_type: cosine
63
- - num_epochs: 2
64
-
65
- ### Training results
66
-
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
- |:-------------:|:------:|:----:|:---------------:|:--------:|
69
- | No log | 0.8696 | 5 | 0.6812 | 0.8370 |
70
- | No log | 1.7391 | 10 | 0.6684 | 0.8370 |
71
-
72
-
73
- ### Framework versions
74
-
75
- - Transformers 4.42.4
76
- - Pytorch 2.3.1+cu121
77
- - Datasets 2.21.0
78
- - Tokenizers 0.19.1
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: ntu-spml/distilhubert
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - audiofolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilhubert-finetuned-donateacry
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: audiofolder
18
+ type: audiofolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8369565217391305
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
+ # distilhubert-finetuned-donateacry
32
+
33
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.6680
36
+ - Accuracy: 0.8370
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: 0.0005
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 123
59
+ - gradient_accumulation_steps: 8
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: cosine
63
+ - num_epochs: 2
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
69
+ | No log | 0.8696 | 5 | 0.6810 | 0.8370 |
70
+ | No log | 1.7391 | 10 | 0.6680 | 0.8370 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.44.0
76
+ - Pytorch 2.4.0+cpu
77
+ - Datasets 2.21.0
78
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -1,86 +1,86 @@
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": "belly_pain",
53
- "1": "burping",
54
- "2": "discomfort",
55
- "3": "hungry",
56
- "4": "tired"
57
- },
58
- "initializer_range": 0.02,
59
- "intermediate_size": 3072,
60
- "label2id": {
61
- "belly_pain": "0",
62
- "burping": "1",
63
- "discomfort": "2",
64
- "hungry": "3",
65
- "tired": "4"
66
- },
67
- "layer_norm_eps": 1e-05,
68
- "layerdrop": 0.0,
69
- "mask_feature_length": 10,
70
- "mask_feature_min_masks": 0,
71
- "mask_feature_prob": 0.0,
72
- "mask_time_length": 10,
73
- "mask_time_min_masks": 2,
74
- "mask_time_prob": 0.05,
75
- "model_type": "hubert",
76
- "num_attention_heads": 12,
77
- "num_conv_pos_embedding_groups": 16,
78
- "num_conv_pos_embeddings": 128,
79
- "num_feat_extract_layers": 7,
80
- "num_hidden_layers": 2,
81
- "pad_token_id": 0,
82
- "torch_dtype": "float32",
83
- "transformers_version": "4.42.4",
84
- "use_weighted_layer_sum": false,
85
- "vocab_size": 32
86
- }
 
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": "belly_pain",
53
+ "1": "burping",
54
+ "2": "discomfort",
55
+ "3": "hungry",
56
+ "4": "tired"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "belly_pain": "0",
62
+ "burping": "1",
63
+ "discomfort": "2",
64
+ "hungry": "3",
65
+ "tired": "4"
66
+ },
67
+ "layer_norm_eps": 1e-05,
68
+ "layerdrop": 0.0,
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_prob": 0.05,
75
+ "model_type": "hubert",
76
+ "num_attention_heads": 12,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 128,
79
+ "num_feat_extract_layers": 7,
80
+ "num_hidden_layers": 2,
81
+ "pad_token_id": 0,
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.44.0",
84
+ "use_weighted_layer_sum": false,
85
+ "vocab_size": 32
86
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321f292c3a37872692ce45daf65a246da803faf205974e181eb80fc019413fe3
3
  size 94766588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:918e229fcc739079e678d896ed5a3a445cf43b7d2dade6505293786b8a9883be
3
  size 94766588
preprocessor_config.json CHANGED
@@ -1,9 +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
- }
 
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
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb519b15df2536c6823b3275a025a046537fa60fc5217911c406b8d976fffd1e
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0167f1fac8e0ba987a495bed49c28f68834844f12647759f1a9b592c9e7986a3
3
  size 5176