Hugging Face's logo

A-POR-LOS-8000
/
distilhubert-finetuned-cry-detector

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Marcos12886 commited on
Commit
ee61ac2
•
1 Parent(s): 119c958

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +45 -3
  2. checkpoint-102/config.json +80 -0
  3. checkpoint-102/model.safetensors +3 -0
  4. checkpoint-102/optimizer.pt +3 -0
  5. checkpoint-102/preprocessor_config.json +9 -0
  6. checkpoint-102/rng_state.pth +3 -0
  7. checkpoint-102/scheduler.pt +3 -0
  8. checkpoint-102/trainer_state.json +138 -0
  9. checkpoint-102/training_args.bin +3 -0
  10. checkpoint-114/config.json +80 -0
  11. checkpoint-114/model.safetensors +3 -0
  12. checkpoint-114/optimizer.pt +3 -0
  13. checkpoint-114/preprocessor_config.json +9 -0
  14. checkpoint-114/rng_state.pth +3 -0
  15. checkpoint-114/scheduler.pt +3 -0
  16. checkpoint-114/trainer_state.json +150 -0
  17. checkpoint-114/training_args.bin +3 -0
  18. checkpoint-12/model.safetensors +1 -1
  19. checkpoint-12/optimizer.pt +1 -1
  20. checkpoint-12/rng_state.pth +1 -1
  21. checkpoint-12/scheduler.pt +1 -1
  22. checkpoint-12/trainer_state.json +13 -13
  23. checkpoint-12/training_args.bin +1 -1
  24. checkpoint-120/config.json +80 -0
  25. checkpoint-120/model.safetensors +3 -0
  26. checkpoint-120/optimizer.pt +3 -0
  27. checkpoint-120/preprocessor_config.json +9 -0
  28. checkpoint-120/rng_state.pth +3 -0
  29. checkpoint-120/scheduler.pt +3 -0
  30. checkpoint-120/trainer_state.json +162 -0
  31. checkpoint-120/training_args.bin +3 -0
  32. checkpoint-25/model.safetensors +1 -1
  33. checkpoint-25/optimizer.pt +1 -1
  34. checkpoint-25/rng_state.pth +2 -2
  35. checkpoint-25/scheduler.pt +1 -1
  36. checkpoint-25/trainer_state.json +20 -20
  37. checkpoint-25/training_args.bin +1 -1
  38. checkpoint-38/model.safetensors +1 -1
  39. checkpoint-38/optimizer.pt +1 -1
  40. checkpoint-38/rng_state.pth +2 -2
  41. checkpoint-38/scheduler.pt +1 -1
  42. checkpoint-38/trainer_state.json +28 -28
  43. checkpoint-38/training_args.bin +1 -1
  44. checkpoint-51/model.safetensors +1 -1
  45. checkpoint-51/optimizer.pt +1 -1
  46. checkpoint-51/rng_state.pth +2 -2
  47. checkpoint-51/scheduler.pt +1 -1
  48. checkpoint-51/trainer_state.json +36 -36
  49. checkpoint-51/training_args.bin +1 -1
  50. checkpoint-63/model.safetensors +1 -1
README.md CHANGED
@@ -6,9 +6,36 @@ tags:
6
  - generated_from_trainer
7
  datasets:
8
  - audiofolder
 
 
 
 
 
9
  model-index:
10
  - name: distilhubert-finetuned-cry-detector
11
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +44,12 @@ should probably proofread and complete it, then remove this comment. -->
17
  # distilhubert-finetuned-cry-detector
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
 
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -44,13 +77,22 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.001
47
- - num_epochs: 1
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
53
- | No log | 0.9412 | 12 | 0.3379 | 0.9559 | 0.9555 | 0.9564 | 0.9559 |
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
 
6
  - generated_from_trainer
7
  datasets:
8
  - audiofolder
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ - precision
13
+ - recall
14
  model-index:
15
  - name: distilhubert-finetuned-cry-detector
16
+ results:
17
+ - task:
18
+ name: Audio Classification
19
+ type: audio-classification
20
+ dataset:
21
+ name: audiofolder
22
+ type: audiofolder
23
+ config: default
24
+ split: train
25
+ args: default
26
+ metrics:
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value: 0.9852941176470589
30
+ - name: F1
31
+ type: f1
32
+ value: 0.9853150765112866
33
+ - name: Precision
34
+ type: precision
35
+ value: 0.9853868369053048
36
+ - name: Recall
37
+ type: recall
38
+ value: 0.9852941176470589
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
  # distilhubert-finetuned-cry-detector
45
 
46
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.0332
49
+ - Accuracy: 0.9853
50
+ - F1: 0.9853
51
+ - Precision: 0.9854
52
+ - Recall: 0.9853
53
 
54
  ## Model description
55
 
 
77
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
78
  - lr_scheduler_type: cosine
79
  - lr_scheduler_warmup_ratio: 0.001
80
+ - num_epochs: 10
81
 
82
  ### Training results
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
+ | No log | 0.9412 | 12 | 0.1931 | 0.9363 | 0.9365 | 0.9372 | 0.9363 |
87
+ | No log | 1.9608 | 25 | 0.0950 | 0.9706 | 0.9704 | 0.9710 | 0.9706 |
88
+ | No log | 2.9804 | 38 | 0.0611 | 0.9804 | 0.9804 | 0.9804 | 0.9804 |
89
+ | No log | 4.0 | 51 | 0.0492 | 0.9853 | 0.9853 | 0.9853 | 0.9853 |
90
+ | No log | 4.9412 | 63 | 0.0588 | 0.9804 | 0.9805 | 0.9814 | 0.9804 |
91
+ | No log | 5.9608 | 76 | 0.0368 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
92
+ | No log | 6.9804 | 89 | 0.0382 | 0.9902 | 0.9902 | 0.9903 | 0.9902 |
93
+ | No log | 8.0 | 102 | 0.0318 | 0.9951 | 0.9951 | 0.9951 | 0.9951 |
94
+ | No log | 8.9412 | 114 | 0.0331 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
95
+ | No log | 9.4118 | 120 | 0.0332 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
96
 
97
 
98
  ### Framework versions
checkpoint-102/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "crying",
53
+ "1": "no_crying"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "label2id": {
58
+ "crying": "0",
59
+ "no_crying": "1"
60
+ },
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "hubert",
70
+ "num_attention_heads": 12,
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_hidden_layers": 2,
75
+ "pad_token_id": 0,
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.44.2",
78
+ "use_weighted_layer_sum": false,
79
+ "vocab_size": 32
80
+ }
checkpoint-102/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098c90d2cba195ac20033090c5954f7ef596abcdeebba724cb1365151033b05e
3
+ size 94763496
checkpoint-102/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6038d1ad5c694fa39b163e31b2ae8b290c47bf72179e6f7edebc2516088a6742
3
+ size 189552570
checkpoint-102/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
+ }
checkpoint-102/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e516bd48eedd1efdcdab1bc63eb245ee5f25372c9b0345efbc5ed2cd8b1b542
3
+ size 14308
checkpoint-102/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0f7d0de8839ca69a8acf7eae5d4a6ab5235d97ffbdfee2586222c3a1d5f473
3
+ size 1064
checkpoint-102/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9950980392156863,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 102,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
+ "step": 12
22
+ },
23
+ {
24
+ "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9705882352941176,
26
+ "eval_f1": 0.9704025549613785,
27
+ "eval_loss": 0.09495726972818375,
28
+ "eval_precision": 0.971039759187257,
29
+ "eval_recall": 0.9705882352941176,
30
+ "eval_runtime": 3.1171,
31
+ "eval_samples_per_second": 65.446,
32
+ "eval_steps_per_second": 8.341,
33
+ "step": 25
34
+ },
35
+ {
36
+ "epoch": 2.980392156862745,
37
+ "eval_accuracy": 0.9803921568627451,
38
+ "eval_f1": 0.9803921568627451,
39
+ "eval_loss": 0.06114682927727699,
40
+ "eval_precision": 0.9803921568627451,
41
+ "eval_recall": 0.9803921568627451,
42
+ "eval_runtime": 3.2163,
43
+ "eval_samples_per_second": 63.428,
44
+ "eval_steps_per_second": 8.084,
45
+ "step": 38
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.9852941176470589,
50
+ "eval_f1": 0.9852722698274712,
51
+ "eval_loss": 0.049169763922691345,
52
+ "eval_precision": 0.9853018065952722,
53
+ "eval_recall": 0.9852941176470589,
54
+ "eval_runtime": 3.1223,
55
+ "eval_samples_per_second": 65.336,
56
+ "eval_steps_per_second": 8.327,
57
+ "step": 51
58
+ },
59
+ {
60
+ "epoch": 4.9411764705882355,
61
+ "eval_accuracy": 0.9803921568627451,
62
+ "eval_f1": 0.9804969685242518,
63
+ "eval_loss": 0.05879249796271324,
64
+ "eval_precision": 0.9813976872800402,
65
+ "eval_recall": 0.9803921568627451,
66
+ "eval_runtime": 3.1449,
67
+ "eval_samples_per_second": 64.868,
68
+ "eval_steps_per_second": 8.267,
69
+ "step": 63
70
+ },
71
+ {
72
+ "epoch": 5.96078431372549,
73
+ "eval_accuracy": 0.9852941176470589,
74
+ "eval_f1": 0.9853150765112866,
75
+ "eval_loss": 0.03680075705051422,
76
+ "eval_precision": 0.9853868369053048,
77
+ "eval_recall": 0.9852941176470589,
78
+ "eval_runtime": 3.1698,
79
+ "eval_samples_per_second": 64.358,
80
+ "eval_steps_per_second": 8.203,
81
+ "step": 76
82
+ },
83
+ {
84
+ "epoch": 6.980392156862745,
85
+ "eval_accuracy": 0.9901960784313726,
86
+ "eval_f1": 0.9901663478316141,
87
+ "eval_loss": 0.0382298119366169,
88
+ "eval_precision": 0.9903446226975638,
89
+ "eval_recall": 0.9901960784313726,
90
+ "eval_runtime": 3.1376,
91
+ "eval_samples_per_second": 65.019,
92
+ "eval_steps_per_second": 8.287,
93
+ "step": 89
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.9950980392156863,
98
+ "eval_f1": 0.995090756609157,
99
+ "eval_loss": 0.03175761550664902,
100
+ "eval_precision": 0.995135458763658,
101
+ "eval_recall": 0.9950980392156863,
102
+ "eval_runtime": 2.949,
103
+ "eval_samples_per_second": 69.175,
104
+ "eval_steps_per_second": 8.816,
105
+ "step": 102
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 120,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 10,
112
+ "save_steps": 500,
113
+ "stateful_callbacks": {
114
+ "EarlyStoppingCallback": {
115
+ "args": {
116
+ "early_stopping_patience": 3,
117
+ "early_stopping_threshold": 0.0
118
+ },
119
+ "attributes": {
120
+ "early_stopping_patience_counter": 0
121
+ }
122
+ },
123
+ "TrainerControl": {
124
+ "args": {
125
+ "should_epoch_stop": false,
126
+ "should_evaluate": false,
127
+ "should_log": false,
128
+ "should_save": true,
129
+ "should_training_stop": false
130
+ },
131
+ "attributes": {}
132
+ }
133
+ },
134
+ "total_flos": 1.052064945063383e+17,
135
+ "train_batch_size": 8,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
checkpoint-102/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
+ size 5240
checkpoint-114/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "crying",
53
+ "1": "no_crying"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "label2id": {
58
+ "crying": "0",
59
+ "no_crying": "1"
60
+ },
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "hubert",
70
+ "num_attention_heads": 12,
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_hidden_layers": 2,
75
+ "pad_token_id": 0,
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.44.2",
78
+ "use_weighted_layer_sum": false,
79
+ "vocab_size": 32
80
+ }
checkpoint-114/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b910bf6b8ec6e19d58a4b52c50de712e949fcdaeece42948112d2e5d95e8f47c
3
+ size 94763496
checkpoint-114/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b95917e0620b5556323a8c02ab048666c97ab19fb25f8fa5f1554c0bfc225f
3
+ size 189552570
checkpoint-114/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
+ }
checkpoint-114/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636081736c072d4bb3052b5541d861668c6c103f9a3ad62f001239e9a3a36fb1
3
+ size 14308
checkpoint-114/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fde2346e00a3c4644832268d0eaddcd20d8548145016394246c018bb8a28ba1
3
+ size 1064
checkpoint-114/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9950980392156863,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
4
+ "epoch": 8.941176470588236,
5
+ "eval_steps": 500,
6
+ "global_step": 114,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
+ "step": 12
22
+ },
23
+ {
24
+ "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9705882352941176,
26
+ "eval_f1": 0.9704025549613785,
27
+ "eval_loss": 0.09495726972818375,
28
+ "eval_precision": 0.971039759187257,
29
+ "eval_recall": 0.9705882352941176,
30
+ "eval_runtime": 3.1171,
31
+ "eval_samples_per_second": 65.446,
32
+ "eval_steps_per_second": 8.341,
33
+ "step": 25
34
+ },
35
+ {
36
+ "epoch": 2.980392156862745,
37
+ "eval_accuracy": 0.9803921568627451,
38
+ "eval_f1": 0.9803921568627451,
39
+ "eval_loss": 0.06114682927727699,
40
+ "eval_precision": 0.9803921568627451,
41
+ "eval_recall": 0.9803921568627451,
42
+ "eval_runtime": 3.2163,
43
+ "eval_samples_per_second": 63.428,
44
+ "eval_steps_per_second": 8.084,
45
+ "step": 38
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.9852941176470589,
50
+ "eval_f1": 0.9852722698274712,
51
+ "eval_loss": 0.049169763922691345,
52
+ "eval_precision": 0.9853018065952722,
53
+ "eval_recall": 0.9852941176470589,
54
+ "eval_runtime": 3.1223,
55
+ "eval_samples_per_second": 65.336,
56
+ "eval_steps_per_second": 8.327,
57
+ "step": 51
58
+ },
59
+ {
60
+ "epoch": 4.9411764705882355,
61
+ "eval_accuracy": 0.9803921568627451,
62
+ "eval_f1": 0.9804969685242518,
63
+ "eval_loss": 0.05879249796271324,
64
+ "eval_precision": 0.9813976872800402,
65
+ "eval_recall": 0.9803921568627451,
66
+ "eval_runtime": 3.1449,
67
+ "eval_samples_per_second": 64.868,
68
+ "eval_steps_per_second": 8.267,
69
+ "step": 63
70
+ },
71
+ {
72
+ "epoch": 5.96078431372549,
73
+ "eval_accuracy": 0.9852941176470589,
74
+ "eval_f1": 0.9853150765112866,
75
+ "eval_loss": 0.03680075705051422,
76
+ "eval_precision": 0.9853868369053048,
77
+ "eval_recall": 0.9852941176470589,
78
+ "eval_runtime": 3.1698,
79
+ "eval_samples_per_second": 64.358,
80
+ "eval_steps_per_second": 8.203,
81
+ "step": 76
82
+ },
83
+ {
84
+ "epoch": 6.980392156862745,
85
+ "eval_accuracy": 0.9901960784313726,
86
+ "eval_f1": 0.9901663478316141,
87
+ "eval_loss": 0.0382298119366169,
88
+ "eval_precision": 0.9903446226975638,
89
+ "eval_recall": 0.9901960784313726,
90
+ "eval_runtime": 3.1376,
91
+ "eval_samples_per_second": 65.019,
92
+ "eval_steps_per_second": 8.287,
93
+ "step": 89
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.9950980392156863,
98
+ "eval_f1": 0.995090756609157,
99
+ "eval_loss": 0.03175761550664902,
100
+ "eval_precision": 0.995135458763658,
101
+ "eval_recall": 0.9950980392156863,
102
+ "eval_runtime": 2.949,
103
+ "eval_samples_per_second": 69.175,
104
+ "eval_steps_per_second": 8.816,
105
+ "step": 102
106
+ },
107
+ {
108
+ "epoch": 8.941176470588236,
109
+ "eval_accuracy": 0.9852941176470589,
110
+ "eval_f1": 0.9853150765112866,
111
+ "eval_loss": 0.033123087137937546,
112
+ "eval_precision": 0.9853868369053048,
113
+ "eval_recall": 0.9852941176470589,
114
+ "eval_runtime": 2.9458,
115
+ "eval_samples_per_second": 69.251,
116
+ "eval_steps_per_second": 8.826,
117
+ "step": 114
118
+ }
119
+ ],
120
+ "logging_steps": 500,
121
+ "max_steps": 120,
122
+ "num_input_tokens_seen": 0,
123
+ "num_train_epochs": 10,
124
+ "save_steps": 500,
125
+ "stateful_callbacks": {
126
+ "EarlyStoppingCallback": {
127
+ "args": {
128
+ "early_stopping_patience": 3,
129
+ "early_stopping_threshold": 0.0
130
+ },
131
+ "attributes": {
132
+ "early_stopping_patience_counter": 0
133
+ }
134
+ },
135
+ "TrainerControl": {
136
+ "args": {
137
+ "should_epoch_stop": false,
138
+ "should_evaluate": false,
139
+ "should_log": false,
140
+ "should_save": true,
141
+ "should_training_stop": false
142
+ },
143
+ "attributes": {}
144
+ }
145
+ },
146
+ "total_flos": 1.1834894644418458e+17,
147
+ "train_batch_size": 8,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }
checkpoint-114/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
+ size 5240
checkpoint-12/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed24ddc80fbfa0595409861cddf08e518561fbdd7c4461e5edac2ef1da033508
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac774d14fe5167fbe1adddc20941f151440dc32f43d6762bbe9d60a26726e8e
3
  size 94763496
checkpoint-12/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf1fd2bcc1d5386abd738663f70a4cfa450e0389d1bb46d5ebbd8d22ee0082c5
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56315b610ef113026417660dc64000a73d31bcdf367d4ade81935feefcbbb425
3
  size 189552570
checkpoint-12/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dd5e5067cb0b69c310c1cb6eb41548b436585db6c11789bed910bb1926cd7c4
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caebb0abc1e3f29ed8c6d6714ac9331ab5a6b59efbd9b310598bb00f5bca4c19
3
  size 14308
checkpoint-12/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00ac470d61d5b4613444f686474fe5bf71dbe645a07555e3c0011199a78b17ab
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca0321d043e24273cc9815784db5e90a317cada9c48cd156d448ab1591d936c
3
  size 1064
checkpoint-12/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9558823529411765,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-12",
4
  "epoch": 0.9411764705882353,
5
  "eval_steps": 500,
@@ -10,21 +10,21 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
- "eval_accuracy": 0.9558823529411765,
14
- "eval_f1": 0.9555272696227192,
15
- "eval_loss": 0.33786964416503906,
16
- "eval_precision": 0.9564428025638596,
17
- "eval_recall": 0.9558823529411765,
18
- "eval_runtime": 3.0231,
19
- "eval_samples_per_second": 67.479,
20
- "eval_steps_per_second": 8.6,
21
  "step": 12
22
  }
23
  ],
24
  "logging_steps": 500,
25
- "max_steps": 12,
26
  "num_input_tokens_seen": 0,
27
- "num_train_epochs": 1,
28
  "save_steps": 500,
29
  "stateful_callbacks": {
30
  "EarlyStoppingCallback": {
@@ -42,12 +42,12 @@
42
  "should_evaluate": false,
43
  "should_log": false,
44
  "should_save": true,
45
- "should_training_stop": true
46
  },
47
  "attributes": {}
48
  }
49
  },
50
- "total_flos": 1.238025689554944e+16,
51
  "train_batch_size": 8,
52
  "trial_name": null,
53
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9362745098039216,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-12",
4
  "epoch": 0.9411764705882353,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
  "step": 12
22
  }
23
  ],
24
  "logging_steps": 500,
25
+ "max_steps": 120,
26
  "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 10,
28
  "save_steps": 500,
29
  "stateful_callbacks": {
30
  "EarlyStoppingCallback": {
 
42
  "should_evaluate": false,
43
  "should_log": false,
44
  "should_save": true,
45
+ "should_training_stop": false
46
  },
47
  "attributes": {}
48
  }
49
  },
50
+ "total_flos": 1.315729776671232e+16,
51
  "train_batch_size": 8,
52
  "trial_name": null,
53
  "trial_params": null
checkpoint-12/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1c27b4ecab2c1ddc610f4ce2ead133759bcabe788a27ce90b2b23560c4e6ad3
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
  size 5240
checkpoint-120/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "crying",
53
+ "1": "no_crying"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "label2id": {
58
+ "crying": "0",
59
+ "no_crying": "1"
60
+ },
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "hubert",
70
+ "num_attention_heads": 12,
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_hidden_layers": 2,
75
+ "pad_token_id": 0,
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.44.2",
78
+ "use_weighted_layer_sum": false,
79
+ "vocab_size": 32
80
+ }
checkpoint-120/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3258e17c3151e1d9899b5ecaa38ee7208137f2c975f17a7f66834494fb6f1ddb
3
+ size 94763496
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67e947c82c7eff62fe82e2161b429d0f674dcb710ae9e066c9aaeaa53719096
3
+ size 189552570
checkpoint-120/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
+ }
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286671099adfaa4371e8fead24d8a5f622004012b7f075f68979922946bd3511
3
+ size 14308
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2409fb1c3fd1c2de2c63b5459c49a97abc9a50084af4337cc5090c00ef975a6
3
+ size 1064
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9950980392156863,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
4
+ "epoch": 9.411764705882353,
5
+ "eval_steps": 500,
6
+ "global_step": 120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
+ "step": 12
22
+ },
23
+ {
24
+ "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9705882352941176,
26
+ "eval_f1": 0.9704025549613785,
27
+ "eval_loss": 0.09495726972818375,
28
+ "eval_precision": 0.971039759187257,
29
+ "eval_recall": 0.9705882352941176,
30
+ "eval_runtime": 3.1171,
31
+ "eval_samples_per_second": 65.446,
32
+ "eval_steps_per_second": 8.341,
33
+ "step": 25
34
+ },
35
+ {
36
+ "epoch": 2.980392156862745,
37
+ "eval_accuracy": 0.9803921568627451,
38
+ "eval_f1": 0.9803921568627451,
39
+ "eval_loss": 0.06114682927727699,
40
+ "eval_precision": 0.9803921568627451,
41
+ "eval_recall": 0.9803921568627451,
42
+ "eval_runtime": 3.2163,
43
+ "eval_samples_per_second": 63.428,
44
+ "eval_steps_per_second": 8.084,
45
+ "step": 38
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.9852941176470589,
50
+ "eval_f1": 0.9852722698274712,
51
+ "eval_loss": 0.049169763922691345,
52
+ "eval_precision": 0.9853018065952722,
53
+ "eval_recall": 0.9852941176470589,
54
+ "eval_runtime": 3.1223,
55
+ "eval_samples_per_second": 65.336,
56
+ "eval_steps_per_second": 8.327,
57
+ "step": 51
58
+ },
59
+ {
60
+ "epoch": 4.9411764705882355,
61
+ "eval_accuracy": 0.9803921568627451,
62
+ "eval_f1": 0.9804969685242518,
63
+ "eval_loss": 0.05879249796271324,
64
+ "eval_precision": 0.9813976872800402,
65
+ "eval_recall": 0.9803921568627451,
66
+ "eval_runtime": 3.1449,
67
+ "eval_samples_per_second": 64.868,
68
+ "eval_steps_per_second": 8.267,
69
+ "step": 63
70
+ },
71
+ {
72
+ "epoch": 5.96078431372549,
73
+ "eval_accuracy": 0.9852941176470589,
74
+ "eval_f1": 0.9853150765112866,
75
+ "eval_loss": 0.03680075705051422,
76
+ "eval_precision": 0.9853868369053048,
77
+ "eval_recall": 0.9852941176470589,
78
+ "eval_runtime": 3.1698,
79
+ "eval_samples_per_second": 64.358,
80
+ "eval_steps_per_second": 8.203,
81
+ "step": 76
82
+ },
83
+ {
84
+ "epoch": 6.980392156862745,
85
+ "eval_accuracy": 0.9901960784313726,
86
+ "eval_f1": 0.9901663478316141,
87
+ "eval_loss": 0.0382298119366169,
88
+ "eval_precision": 0.9903446226975638,
89
+ "eval_recall": 0.9901960784313726,
90
+ "eval_runtime": 3.1376,
91
+ "eval_samples_per_second": 65.019,
92
+ "eval_steps_per_second": 8.287,
93
+ "step": 89
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.9950980392156863,
98
+ "eval_f1": 0.995090756609157,
99
+ "eval_loss": 0.03175761550664902,
100
+ "eval_precision": 0.995135458763658,
101
+ "eval_recall": 0.9950980392156863,
102
+ "eval_runtime": 2.949,
103
+ "eval_samples_per_second": 69.175,
104
+ "eval_steps_per_second": 8.816,
105
+ "step": 102
106
+ },
107
+ {
108
+ "epoch": 8.941176470588236,
109
+ "eval_accuracy": 0.9852941176470589,
110
+ "eval_f1": 0.9853150765112866,
111
+ "eval_loss": 0.033123087137937546,
112
+ "eval_precision": 0.9853868369053048,
113
+ "eval_recall": 0.9852941176470589,
114
+ "eval_runtime": 2.9458,
115
+ "eval_samples_per_second": 69.251,
116
+ "eval_steps_per_second": 8.826,
117
+ "step": 114
118
+ },
119
+ {
120
+ "epoch": 9.411764705882353,
121
+ "eval_accuracy": 0.9852941176470589,
122
+ "eval_f1": 0.9853150765112866,
123
+ "eval_loss": 0.033173661679029465,
124
+ "eval_precision": 0.9853868369053048,
125
+ "eval_recall": 0.9852941176470589,
126
+ "eval_runtime": 2.9666,
127
+ "eval_samples_per_second": 68.766,
128
+ "eval_steps_per_second": 8.764,
129
+ "step": 120
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 120,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 10,
136
+ "save_steps": 500,
137
+ "stateful_callbacks": {
138
+ "EarlyStoppingCallback": {
139
+ "args": {
140
+ "early_stopping_patience": 3,
141
+ "early_stopping_threshold": 0.0
142
+ },
143
+ "attributes": {
144
+ "early_stopping_patience_counter": 0
145
+ }
146
+ },
147
+ "TrainerControl": {
148
+ "args": {
149
+ "should_epoch_stop": false,
150
+ "should_evaluate": false,
151
+ "should_log": false,
152
+ "should_save": true,
153
+ "should_training_stop": true
154
+ },
155
+ "attributes": {}
156
+ }
157
+ },
158
+ "total_flos": 1.237670053721906e+17,
159
+ "train_batch_size": 8,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
+ size 5240
checkpoint-25/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:457aaf1ca73f2bd8fdf652ff897b1db85473a23401cdea192ccda04c31e902f9
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1949ab9da06d9f94ddb053df98c408f27159d75669cf1d2eb4e1cc47323344
3
  size 94763496
checkpoint-25/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f78eeb88abcee76fe1f3cb427847a3366d60d465ad4933bdf631baef11c677d
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fe5dbcc580831e63b26cf1b5d7e9409f5b456d1141636612d7fca115a01a87
3
  size 189552570
checkpoint-25/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e5c954d42fa0d2b945cf8a644f5bb95c0ecae8f78ef6f89815808920b5b330c
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272c079a133d684090b7a24b10497f4bd703dbf9ecfecafe1a788c62b4404ce6
3
+ size 14308
checkpoint-25/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91532783b102a4c8ff5ee86df37d3662ca7a62e198729a349c132e2c9a68d5d0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6633f18d367676ea03844228fc7112a6a9464032824bb5f9f17a85ee888f12e8
3
  size 1064
checkpoint-25/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9558823529411765,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-25",
4
  "epoch": 1.9607843137254903,
5
  "eval_steps": 500,
@@ -10,33 +10,33 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
- "eval_accuracy": 0.9509803921568627,
14
- "eval_f1": 0.9509803921568627,
15
- "eval_loss": 0.19337645173072815,
16
- "eval_precision": 0.9509803921568627,
17
- "eval_recall": 0.9509803921568627,
18
- "eval_runtime": 2.9937,
19
- "eval_samples_per_second": 68.144,
20
- "eval_steps_per_second": 8.685,
21
  "step": 12
22
  },
23
  {
24
  "epoch": 1.9607843137254903,
25
- "eval_accuracy": 0.9558823529411765,
26
- "eval_f1": 0.9558168094824137,
27
- "eval_loss": 0.11207430809736252,
28
- "eval_precision": 0.9558008500901145,
29
- "eval_recall": 0.9558823529411765,
30
- "eval_runtime": 2.9789,
31
- "eval_samples_per_second": 68.481,
32
- "eval_steps_per_second": 8.728,
33
  "step": 25
34
  }
35
  ],
36
  "logging_steps": 500,
37
- "max_steps": 48,
38
  "num_input_tokens_seen": 0,
39
- "num_train_epochs": 4,
40
  "save_steps": 500,
41
  "stateful_callbacks": {
42
  "EarlyStoppingCallback": {
@@ -59,7 +59,7 @@
59
  "attributes": {}
60
  }
61
  },
62
- "total_flos": 2.632285534507315e+16,
63
  "train_batch_size": 8,
64
  "trial_name": null,
65
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9705882352941176,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-25",
4
  "epoch": 1.9607843137254903,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
  "step": 12
22
  },
23
  {
24
  "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9705882352941176,
26
+ "eval_f1": 0.9704025549613785,
27
+ "eval_loss": 0.09495726972818375,
28
+ "eval_precision": 0.971039759187257,
29
+ "eval_recall": 0.9705882352941176,
30
+ "eval_runtime": 3.1171,
31
+ "eval_samples_per_second": 65.446,
32
+ "eval_steps_per_second": 8.341,
33
  "step": 25
34
  }
35
  ],
36
  "logging_steps": 500,
37
+ "max_steps": 120,
38
  "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 10,
40
  "save_steps": 500,
41
  "stateful_callbacks": {
42
  "EarlyStoppingCallback": {
 
59
  "attributes": {}
60
  }
61
  },
62
+ "total_flos": 2.630848254506803e+16,
63
  "train_batch_size": 8,
64
  "trial_name": null,
65
  "trial_params": null
checkpoint-25/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08c1ef2199623b781e926f1d827964186fca47326620731302bfe37c5d058b9
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
  size 5240
checkpoint-38/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:365a9fb794f55008ff39b21086b11700c109a194efb2127a6db2145604a614b6
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8bc28d8ebd1dbdd73656a784624c72928eb10e21d9e6acdce2e1d312d787010
3
  size 94763496
checkpoint-38/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:198372300c7cb71ea5cd197e4b8f17970da74cfc971f4a284751e8c5c2fe5397
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee1b6c4df5d7a5ef50f7350cb964bab9875222b057b8eb71768826fceb9156f
3
  size 189552570
checkpoint-38/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:780c51c50482e6e8f628b4687957abc3bb4ff7f96b977c02d8538cf6f0d2d494
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d19f57e20f91b35ae6289880b02cdfa14033ed6b20b4d1730bfb179a9264102
3
+ size 14308
checkpoint-38/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96ddec5715a7e2a3cc7175b7f159a7e1fd2303094015b4bffdae6a236e889974
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df84074f7631c8ca35330b9e20d4190996409e954261c1b476ad0fabe74b93b
3
  size 1064
checkpoint-38/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9607843137254902,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-38",
4
  "epoch": 2.980392156862745,
5
  "eval_steps": 500,
@@ -10,45 +10,45 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
- "eval_accuracy": 0.9509803921568627,
14
- "eval_f1": 0.9509803921568627,
15
- "eval_loss": 0.19337645173072815,
16
- "eval_precision": 0.9509803921568627,
17
- "eval_recall": 0.9509803921568627,
18
- "eval_runtime": 2.9937,
19
- "eval_samples_per_second": 68.144,
20
- "eval_steps_per_second": 8.685,
21
  "step": 12
22
  },
23
  {
24
  "epoch": 1.9607843137254903,
25
- "eval_accuracy": 0.9558823529411765,
26
- "eval_f1": 0.9558168094824137,
27
- "eval_loss": 0.11207430809736252,
28
- "eval_precision": 0.9558008500901145,
29
- "eval_recall": 0.9558823529411765,
30
- "eval_runtime": 2.9789,
31
- "eval_samples_per_second": 68.481,
32
- "eval_steps_per_second": 8.728,
33
  "step": 25
34
  },
35
  {
36
  "epoch": 2.980392156862745,
37
- "eval_accuracy": 0.9607843137254902,
38
- "eval_f1": 0.9608937528499771,
39
- "eval_loss": 0.08983828127384186,
40
- "eval_precision": 0.9611995291537668,
41
- "eval_recall": 0.9607843137254902,
42
- "eval_runtime": 2.927,
43
- "eval_samples_per_second": 69.695,
44
- "eval_steps_per_second": 8.883,
45
  "step": 38
46
  }
47
  ],
48
  "logging_steps": 500,
49
- "max_steps": 48,
50
  "num_input_tokens_seen": 0,
51
- "num_train_epochs": 4,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "EarlyStoppingCallback": {
@@ -71,7 +71,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 3.947040143988326e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9803921568627451,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-38",
4
  "epoch": 2.980392156862745,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
  "step": 12
22
  },
23
  {
24
  "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9705882352941176,
26
+ "eval_f1": 0.9704025549613785,
27
+ "eval_loss": 0.09495726972818375,
28
+ "eval_precision": 0.971039759187257,
29
+ "eval_recall": 0.9705882352941176,
30
+ "eval_runtime": 3.1171,
31
+ "eval_samples_per_second": 65.446,
32
+ "eval_steps_per_second": 8.341,
33
  "step": 25
34
  },
35
  {
36
  "epoch": 2.980392156862745,
37
+ "eval_accuracy": 0.9803921568627451,
38
+ "eval_f1": 0.9803921568627451,
39
+ "eval_loss": 0.06114682927727699,
40
+ "eval_precision": 0.9803921568627451,
41
+ "eval_recall": 0.9803921568627451,
42
+ "eval_runtime": 3.2163,
43
+ "eval_samples_per_second": 63.428,
44
+ "eval_steps_per_second": 8.084,
45
  "step": 38
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 120,
50
  "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 10,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "EarlyStoppingCallback": {
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 3.946056334924685e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null
checkpoint-38/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08c1ef2199623b781e926f1d827964186fca47326620731302bfe37c5d058b9
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
  size 5240
checkpoint-51/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e9b6729c50f84d9b261120a8e72c4b3a3da69e27bb43431fdcd37c673c45006
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072781416d7434132c8e1b73276d4503dca0b1b8db503afa1a8ba07bc69b3ae9
3
  size 94763496
checkpoint-51/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:461ec76d1bc7a1e71c52a5302f7d5be7e5eec1ad9fc45cdec1c8d7a0e5e545c1
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da71c2ca09d32a4c673ba10e3259d6198c7a2fbaa9004a4a0eaa7d9cc8d8fecb
3
  size 189552570
checkpoint-51/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bfb428aabf8fc7d0150525679311cfec661fbbda39191a37add4ec1737f1b54
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc415b22b0f41c29b31b3bf40c83a0c3865a35793ba92c48d3d575e69ed5279
3
+ size 14308
checkpoint-51/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec8121eea0c42c283a1e74848057f68b938b9185ee7ce8d2f0f77b15cf4fe84
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f2e94f9942cdbd4528ad8ed9baf4498c04d7503c2ef6dab9521dfcb4021a49
3
  size 1064
checkpoint-51/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9705882352941176,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-51",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
@@ -10,57 +10,57 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
- "eval_accuracy": 0.9558823529411765,
14
- "eval_f1": 0.9558168094824137,
15
- "eval_loss": 0.18768352270126343,
16
- "eval_precision": 0.9558008500901145,
17
- "eval_recall": 0.9558823529411765,
18
- "eval_runtime": 3.1767,
19
- "eval_samples_per_second": 64.218,
20
- "eval_steps_per_second": 8.185,
21
  "step": 12
22
  },
23
  {
24
  "epoch": 1.9607843137254903,
25
- "eval_accuracy": 0.9607843137254902,
26
- "eval_f1": 0.9603980954872683,
27
- "eval_loss": 0.10839918255805969,
28
- "eval_precision": 0.961865628604383,
29
- "eval_recall": 0.9607843137254902,
30
- "eval_runtime": 3.1396,
31
- "eval_samples_per_second": 64.977,
32
- "eval_steps_per_second": 8.281,
33
  "step": 25
34
  },
35
  {
36
  "epoch": 2.980392156862745,
37
- "eval_accuracy": 0.9607843137254902,
38
- "eval_f1": 0.9608937528499771,
39
- "eval_loss": 0.07022649049758911,
40
- "eval_precision": 0.9611995291537668,
41
- "eval_recall": 0.9607843137254902,
42
- "eval_runtime": 3.1392,
43
- "eval_samples_per_second": 64.985,
44
- "eval_steps_per_second": 8.282,
45
  "step": 38
46
  },
47
  {
48
  "epoch": 4.0,
49
- "eval_accuracy": 0.9705882352941176,
50
- "eval_f1": 0.9707454527863777,
51
- "eval_loss": 0.05151732638478279,
52
- "eval_precision": 0.9716895305130601,
53
- "eval_recall": 0.9705882352941176,
54
- "eval_runtime": 3.1558,
55
- "eval_samples_per_second": 64.644,
56
- "eval_steps_per_second": 8.239,
57
  "step": 51
58
  }
59
  ],
60
  "logging_steps": 500,
61
- "max_steps": 96,
62
  "num_input_tokens_seen": 0,
63
- "num_train_epochs": 8,
64
  "save_steps": 500,
65
  "stateful_callbacks": {
66
  "EarlyStoppingCallback": {
@@ -83,7 +83,7 @@
83
  "attributes": {}
84
  }
85
  },
86
- "total_flos": 5.25877328162016e+16,
87
  "train_batch_size": 8,
88
  "trial_name": null,
89
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9852941176470589,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-51",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9362745098039216,
14
+ "eval_f1": 0.9365356058160116,
15
+ "eval_loss": 0.19313116371631622,
16
+ "eval_precision": 0.9372234219385678,
17
+ "eval_recall": 0.9362745098039216,
18
+ "eval_runtime": 3.0986,
19
+ "eval_samples_per_second": 65.836,
20
+ "eval_steps_per_second": 8.391,
21
  "step": 12
22
  },
23
  {
24
  "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9705882352941176,
26
+ "eval_f1": 0.9704025549613785,
27
+ "eval_loss": 0.09495726972818375,
28
+ "eval_precision": 0.971039759187257,
29
+ "eval_recall": 0.9705882352941176,
30
+ "eval_runtime": 3.1171,
31
+ "eval_samples_per_second": 65.446,
32
+ "eval_steps_per_second": 8.341,
33
  "step": 25
34
  },
35
  {
36
  "epoch": 2.980392156862745,
37
+ "eval_accuracy": 0.9803921568627451,
38
+ "eval_f1": 0.9803921568627451,
39
+ "eval_loss": 0.06114682927727699,
40
+ "eval_precision": 0.9803921568627451,
41
+ "eval_recall": 0.9803921568627451,
42
+ "eval_runtime": 3.2163,
43
+ "eval_samples_per_second": 63.428,
44
+ "eval_steps_per_second": 8.084,
45
  "step": 38
46
  },
47
  {
48
  "epoch": 4.0,
49
+ "eval_accuracy": 0.9852941176470589,
50
+ "eval_f1": 0.9852722698274712,
51
+ "eval_loss": 0.049169763922691345,
52
+ "eval_precision": 0.9853018065952722,
53
+ "eval_recall": 0.9852941176470589,
54
+ "eval_runtime": 3.1223,
55
+ "eval_samples_per_second": 65.336,
56
+ "eval_steps_per_second": 8.327,
57
  "step": 51
58
  }
59
  ],
60
  "logging_steps": 500,
61
+ "max_steps": 120,
62
  "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 10,
64
  "save_steps": 500,
65
  "stateful_callbacks": {
66
  "EarlyStoppingCallback": {
 
83
  "attributes": {}
84
  }
85
  },
86
+ "total_flos": 5.261731531342733e+16,
87
  "train_batch_size": 8,
88
  "trial_name": null,
89
  "trial_params": null
checkpoint-51/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecc689edbe3573cb27ca0a4ddd21670a9f672918abacfb53cac5b55b680695a7
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
3
  size 5240
checkpoint-63/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc362a1585df3481e2dcd870193d28d930ae325d6150daaaad1493b1996de42f
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1568086524c8dced6705098aa1db3285da46fd4a5391fa6b9d6eb7df4502d4
3
  size 94763496