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
be08ef4
•
1 Parent(s): 5c2a1eb

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 +16 -29
  2. checkpoint-170/model.safetensors +1 -1
  3. checkpoint-170/optimizer.pt +1 -1
  4. checkpoint-170/scheduler.pt +1 -1
  5. checkpoint-170/trainer_state.json +14 -20
  6. checkpoint-170/training_args.bin +1 -1
  7. checkpoint-256/model.safetensors +1 -1
  8. checkpoint-256/optimizer.pt +1 -1
  9. checkpoint-256/scheduler.pt +1 -1
  10. checkpoint-256/trainer_state.json +19 -28
  11. checkpoint-256/training_args.bin +1 -1
  12. checkpoint-341/model.safetensors +1 -1
  13. checkpoint-341/optimizer.pt +1 -1
  14. checkpoint-341/scheduler.pt +1 -1
  15. checkpoint-341/trainer_state.json +23 -35
  16. checkpoint-341/training_args.bin +1 -1
  17. checkpoint-426/model.safetensors +1 -1
  18. checkpoint-426/optimizer.pt +1 -1
  19. checkpoint-426/scheduler.pt +1 -1
  20. checkpoint-426/trainer_state.json +26 -41
  21. checkpoint-426/training_args.bin +1 -1
  22. checkpoint-512/model.safetensors +1 -1
  23. checkpoint-512/optimizer.pt +1 -1
  24. checkpoint-512/scheduler.pt +1 -1
  25. checkpoint-512/trainer_state.json +36 -54
  26. checkpoint-512/training_args.bin +1 -1
  27. checkpoint-597/config.json +80 -0
  28. checkpoint-597/model.safetensors +3 -0
  29. checkpoint-597/optimizer.pt +3 -0
  30. checkpoint-597/rng_state.pth +3 -0
  31. checkpoint-597/scheduler.pt +3 -0
  32. checkpoint-597/trainer_state.json +112 -0
  33. checkpoint-597/training_args.bin +3 -0
  34. checkpoint-683/config.json +80 -0
  35. checkpoint-683/model.safetensors +3 -0
  36. checkpoint-683/optimizer.pt +3 -0
  37. checkpoint-683/rng_state.pth +3 -0
  38. checkpoint-683/scheduler.pt +3 -0
  39. checkpoint-683/trainer_state.json +121 -0
  40. checkpoint-683/training_args.bin +3 -0
  41. checkpoint-768/config.json +80 -0
  42. checkpoint-768/model.safetensors +3 -0
  43. checkpoint-768/optimizer.pt +3 -0
  44. checkpoint-768/rng_state.pth +3 -0
  45. checkpoint-768/scheduler.pt +3 -0
  46. checkpoint-768/trainer_state.json +130 -0
  47. checkpoint-768/training_args.bin +3 -0
  48. checkpoint-85/model.safetensors +1 -1
  49. checkpoint-85/optimizer.pt +1 -1
  50. checkpoint-85/scheduler.pt +1 -1
README.md CHANGED
@@ -8,9 +8,6 @@ datasets:
8
  - audiofolder
9
  metrics:
10
  - accuracy
11
- - f1
12
- - precision
13
- - recall
14
  model-index:
15
  - name: distilhubert-finetuned-cry-detector
16
  results:
@@ -21,21 +18,12 @@ model-index:
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: 0.991941391941392
30
- - name: F1
31
- type: f1
32
- value: 0.9919569277165429
33
- - name: Precision
34
- type: precision
35
- value: 0.9920048531706146
36
- - name: Recall
37
- type: recall
38
- value: 0.991941391941392
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.0408
49
- - Accuracy: 0.9919
50
- - F1: 0.9920
51
- - Precision: 0.9920
52
- - Recall: 0.9919
53
 
54
  ## Model description
55
 
@@ -77,19 +62,21 @@ The following hyperparameters were used during training:
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: 7
81
 
82
  ### Training results
83
 
84
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
- |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
- | No log | 0.9956 | 85 | 0.0736 | 0.9788 | 0.9788 | 0.9790 | 0.9788 |
87
- | No log | 1.9912 | 170 | 0.0680 | 0.9758 | 0.9760 | 0.9770 | 0.9758 |
88
- | No log | 2.9985 | 256 | 0.0447 | 0.9875 | 0.9876 | 0.9876 | 0.9875 |
89
- | No log | 3.9941 | 341 | 0.0452 | 0.9905 | 0.9905 | 0.9905 | 0.9905 |
90
- | No log | 4.9898 | 426 | 0.0439 | 0.9919 | 0.9920 | 0.9920 | 0.9919 |
91
- | 0.053 | 5.9971 | 512 | 0.0401 | 0.9919 | 0.9920 | 0.9920 | 0.9919 |
92
- | 0.053 | 6.9693 | 595 | 0.0408 | 0.9919 | 0.9920 | 0.9920 | 0.9919 |
 
 
93
 
94
 
95
  ### Framework versions
 
8
  - audiofolder
9
  metrics:
10
  - accuracy
 
 
 
11
  model-index:
12
  - name: distilhubert-finetuned-cry-detector
13
  results:
 
18
  name: audiofolder
19
  type: audiofolder
20
  config: default
21
+ split: None
22
  args: default
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9926739926739927
 
 
 
 
 
 
 
 
 
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.0459
37
+ - Accuracy: 0.9927
 
 
 
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: cosine
64
  - lr_scheduler_warmup_ratio: 0.001
65
+ - num_epochs: 10
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.9956 | 85 | 0.0692 | 0.9773 |
72
+ | No log | 1.9912 | 170 | 0.0466 | 0.9861 |
73
+ | No log | 2.9985 | 256 | 0.0489 | 0.9853 |
74
+ | No log | 3.9941 | 341 | 0.0423 | 0.9897 |
75
+ | No log | 4.9898 | 426 | 0.0443 | 0.9919 |
76
+ | 0.055 | 5.9971 | 512 | 0.0434 | 0.9927 |
77
+ | 0.055 | 6.9927 | 597 | 0.0440 | 0.9927 |
78
+ | 0.055 | 8.0 | 683 | 0.0460 | 0.9927 |
79
+ | 0.055 | 8.9956 | 768 | 0.0459 | 0.9927 |
80
 
81
 
82
  ### Framework versions
checkpoint-170/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14ad2529c107706df5e38d4e839c5fe54bbd3638840f1b016ba56f9e40cfd45a
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234766c4455d275002665fd833b44efa39e41bc2661c4bb2462491e9b235265b
3
  size 94763496
checkpoint-170/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feca43a53b1ea22e785cf6aebc67731d4d759491623447479b488904538b9c5d
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54168c775d69b037d7dd954b39f148a62b5d5230761ef39bcb3fc60c2c2b65be
3
  size 189552570
checkpoint-170/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e9632dd1819b93de48e3bbe467fe0d96e895179dd60318df68d501d078c6ed9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2034409269304d3556c2ec17a8e8112c21629214e514ea105efbb26052b23cf
3
  size 1064
checkpoint-170/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9787545787545787,
3
- "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-85",
4
  "epoch": 1.9912152269399708,
5
  "eval_steps": 500,
6
  "global_step": 170,
@@ -10,33 +10,27 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
- "eval_accuracy": 0.9787545787545787,
14
- "eval_f1": 0.9788275754377449,
15
- "eval_loss": 0.07363971322774887,
16
- "eval_precision": 0.9790028856592324,
17
- "eval_recall": 0.9787545787545787,
18
- "eval_runtime": 4.1234,
19
- "eval_samples_per_second": 331.041,
20
- "eval_steps_per_second": 41.471,
21
  "step": 85
22
  },
23
  {
24
  "epoch": 1.9912152269399708,
25
- "eval_accuracy": 0.9758241758241758,
26
- "eval_f1": 0.9760458977669253,
27
- "eval_loss": 0.0680176243185997,
28
- "eval_precision": 0.9770364666252971,
29
- "eval_recall": 0.9758241758241758,
30
- "eval_runtime": 3.9805,
31
- "eval_samples_per_second": 342.924,
32
- "eval_steps_per_second": 42.96,
33
  "step": 170
34
  }
35
  ],
36
  "logging_steps": 500,
37
- "max_steps": 595,
38
  "num_input_tokens_seen": 0,
39
- "num_train_epochs": 7,
40
  "save_steps": 500,
41
  "stateful_callbacks": {
42
  "EarlyStoppingCallback": {
 
1
  {
2
+ "best_metric": 0.9860805860805861,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170",
4
  "epoch": 1.9912152269399708,
5
  "eval_steps": 500,
6
  "global_step": 170,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
 
 
 
18
  "step": 85
19
  },
20
  {
21
  "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
 
 
 
27
  "step": 170
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 850,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 10,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "EarlyStoppingCallback": {
checkpoint-170/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa3df7f2810faa9c35a46d178b12337edb0b134aa27dc1689b302d9bcc9d3d0
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
  size 5240
checkpoint-256/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a88f787681237fee33b288f12593aacb934387bd6da2bb8ff790e9b5a05f9556
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74664b03f722ebd6f388e4906fa982d1ec05522a8b62f38b65182ae0f78dd659
3
  size 94763496
checkpoint-256/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:346b3d592afd4162ca6d18904ccc574e4d170d2fe28c5c444a687f9850fd23b6
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93c7b3a43b80636a934d1782de63f8303fd44e61f41d41d41caa10a9639ffc1
3
  size 189552570
checkpoint-256/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93dfa4ba2e0507f7a6d68626387a161a1bbe6b94f9a9daf967637af5f5748293
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1daa6dfbc632505773869a612096b9f14303a596de4d72e49c6d934621e4204
3
  size 1064
checkpoint-256/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.9875457875457876,
3
- "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-256",
4
  "epoch": 2.998535871156662,
5
  "eval_steps": 500,
6
  "global_step": 256,
@@ -10,45 +10,36 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
- "eval_accuracy": 0.9787545787545787,
14
- "eval_f1": 0.9788275754377449,
15
- "eval_loss": 0.07363971322774887,
16
- "eval_precision": 0.9790028856592324,
17
- "eval_recall": 0.9787545787545787,
18
- "eval_runtime": 4.1234,
19
- "eval_samples_per_second": 331.041,
20
- "eval_steps_per_second": 41.471,
21
  "step": 85
22
  },
23
  {
24
  "epoch": 1.9912152269399708,
25
- "eval_accuracy": 0.9758241758241758,
26
- "eval_f1": 0.9760458977669253,
27
- "eval_loss": 0.0680176243185997,
28
- "eval_precision": 0.9770364666252971,
29
- "eval_recall": 0.9758241758241758,
30
- "eval_runtime": 3.9805,
31
- "eval_samples_per_second": 342.924,
32
- "eval_steps_per_second": 42.96,
33
  "step": 170
34
  },
35
  {
36
  "epoch": 2.998535871156662,
37
- "eval_accuracy": 0.9875457875457876,
38
- "eval_f1": 0.987550637300988,
39
- "eval_loss": 0.044689420610666275,
40
- "eval_precision": 0.9875567820840008,
41
- "eval_recall": 0.9875457875457876,
42
- "eval_runtime": 4.1011,
43
- "eval_samples_per_second": 332.839,
44
- "eval_steps_per_second": 41.696,
45
  "step": 256
46
  }
47
  ],
48
  "logging_steps": 500,
49
- "max_steps": 595,
50
  "num_input_tokens_seen": 0,
51
- "num_train_epochs": 7,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "EarlyStoppingCallback": {
 
1
  {
2
+ "best_metric": 0.9860805860805861,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170",
4
  "epoch": 2.998535871156662,
5
  "eval_steps": 500,
6
  "global_step": 256,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
 
 
 
18
  "step": 85
19
  },
20
  {
21
  "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
 
 
 
27
  "step": 170
28
  },
29
  {
30
  "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
 
 
 
36
  "step": 256
37
  }
38
  ],
39
  "logging_steps": 500,
40
+ "max_steps": 850,
41
  "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 10,
43
  "save_steps": 500,
44
  "stateful_callbacks": {
45
  "EarlyStoppingCallback": {
checkpoint-256/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa3df7f2810faa9c35a46d178b12337edb0b134aa27dc1689b302d9bcc9d3d0
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
  size 5240
checkpoint-341/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d274d762a507f6e75c1d2a58abb70f2a03423ada1370bde55f03f89babb022da
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4695016088987cb75a8381886d078dee5da33d439dfa3472cbded298196975
3
  size 94763496
checkpoint-341/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab5a9612889baf3497db6846ceb8c24a7fa052bc1a8f788d7b5b366a70c8d5b9
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88625b2c249303af96915509b84fbe0fd810785b84d32d68e936f83e44e0c710
3
  size 189552570
checkpoint-341/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db61ebcfff67389442b8098d4cae839f684a87068fe21401504beb7ddd27d04d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0e5f3394e1cb08f5e6ec9d7e11dc43d76ef8c66bf2eaa7a0f848f815b1d4cc
3
  size 1064
checkpoint-341/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.9904761904761905,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341",
4
  "epoch": 3.994143484626647,
5
  "eval_steps": 500,
@@ -10,57 +10,45 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
- "eval_accuracy": 0.9787545787545787,
14
- "eval_f1": 0.9788275754377449,
15
- "eval_loss": 0.07363971322774887,
16
- "eval_precision": 0.9790028856592324,
17
- "eval_recall": 0.9787545787545787,
18
- "eval_runtime": 4.1234,
19
- "eval_samples_per_second": 331.041,
20
- "eval_steps_per_second": 41.471,
21
  "step": 85
22
  },
23
  {
24
  "epoch": 1.9912152269399708,
25
- "eval_accuracy": 0.9758241758241758,
26
- "eval_f1": 0.9760458977669253,
27
- "eval_loss": 0.0680176243185997,
28
- "eval_precision": 0.9770364666252971,
29
- "eval_recall": 0.9758241758241758,
30
- "eval_runtime": 3.9805,
31
- "eval_samples_per_second": 342.924,
32
- "eval_steps_per_second": 42.96,
33
  "step": 170
34
  },
35
  {
36
  "epoch": 2.998535871156662,
37
- "eval_accuracy": 0.9875457875457876,
38
- "eval_f1": 0.987550637300988,
39
- "eval_loss": 0.044689420610666275,
40
- "eval_precision": 0.9875567820840008,
41
- "eval_recall": 0.9875457875457876,
42
- "eval_runtime": 4.1011,
43
- "eval_samples_per_second": 332.839,
44
- "eval_steps_per_second": 41.696,
45
  "step": 256
46
  },
47
  {
48
  "epoch": 3.994143484626647,
49
- "eval_accuracy": 0.9904761904761905,
50
- "eval_f1": 0.9904945509377323,
51
- "eval_loss": 0.045228052884340286,
52
- "eval_precision": 0.9905452314533213,
53
- "eval_recall": 0.9904761904761905,
54
- "eval_runtime": 3.9393,
55
- "eval_samples_per_second": 346.509,
56
- "eval_steps_per_second": 43.409,
57
  "step": 341
58
  }
59
  ],
60
  "logging_steps": 500,
61
- "max_steps": 595,
62
  "num_input_tokens_seen": 0,
63
- "num_train_epochs": 7,
64
  "save_steps": 500,
65
  "stateful_callbacks": {
66
  "EarlyStoppingCallback": {
 
1
  {
2
+ "best_metric": 0.9897435897435898,
3
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341",
4
  "epoch": 3.994143484626647,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
 
 
 
18
  "step": 85
19
  },
20
  {
21
  "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
 
 
 
27
  "step": 170
28
  },
29
  {
30
  "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
 
 
 
36
  "step": 256
37
  },
38
  {
39
  "epoch": 3.994143484626647,
40
+ "eval_accuracy": 0.9897435897435898,
41
+ "eval_loss": 0.04228556528687477,
42
+ "eval_runtime": 15.2931,
43
+ "eval_samples_per_second": 89.256,
44
+ "eval_steps_per_second": 11.181,
 
 
 
45
  "step": 341
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 850,
50
  "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 10,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "EarlyStoppingCallback": {
checkpoint-341/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa3df7f2810faa9c35a46d178b12337edb0b134aa27dc1689b302d9bcc9d3d0
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
  size 5240
checkpoint-426/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94760f7df9dc2c6bad702593ec0871720fa6ae352e88f79c71bcfccc8fab1a09
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14ac9c4fea572b7ef6e0e3502f94a78d1c0c3fef295cf4a6f6746aeac8feaf9
3
  size 94763496
checkpoint-426/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6550e976738f22f913650571284f8eb12dea30c8877134bbe84a1ebd7a73b5e
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bfbb9842afd0e0e7c548c18e2442c293c57767268f19e3c10c10c38c6745a66
3
  size 189552570
checkpoint-426/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1894ac3a34350cc065802675cae4d32438918a7d772edc033390240aaf5d8841
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d495ecbbc4c3121c1feab1c93a2d37084137f7007f1d94685663700a6993c70
3
  size 1064
checkpoint-426/trainer_state.json CHANGED
@@ -10,69 +10,54 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
- "eval_accuracy": 0.9787545787545787,
14
- "eval_f1": 0.9788275754377449,
15
- "eval_loss": 0.07363971322774887,
16
- "eval_precision": 0.9790028856592324,
17
- "eval_recall": 0.9787545787545787,
18
- "eval_runtime": 4.1234,
19
- "eval_samples_per_second": 331.041,
20
- "eval_steps_per_second": 41.471,
21
  "step": 85
22
  },
23
  {
24
  "epoch": 1.9912152269399708,
25
- "eval_accuracy": 0.9758241758241758,
26
- "eval_f1": 0.9760458977669253,
27
- "eval_loss": 0.0680176243185997,
28
- "eval_precision": 0.9770364666252971,
29
- "eval_recall": 0.9758241758241758,
30
- "eval_runtime": 3.9805,
31
- "eval_samples_per_second": 342.924,
32
- "eval_steps_per_second": 42.96,
33
  "step": 170
34
  },
35
  {
36
  "epoch": 2.998535871156662,
37
- "eval_accuracy": 0.9875457875457876,
38
- "eval_f1": 0.987550637300988,
39
- "eval_loss": 0.044689420610666275,
40
- "eval_precision": 0.9875567820840008,
41
- "eval_recall": 0.9875457875457876,
42
- "eval_runtime": 4.1011,
43
- "eval_samples_per_second": 332.839,
44
- "eval_steps_per_second": 41.696,
45
  "step": 256
46
  },
47
  {
48
  "epoch": 3.994143484626647,
49
- "eval_accuracy": 0.9904761904761905,
50
- "eval_f1": 0.9904945509377323,
51
- "eval_loss": 0.045228052884340286,
52
- "eval_precision": 0.9905452314533213,
53
- "eval_recall": 0.9904761904761905,
54
- "eval_runtime": 3.9393,
55
- "eval_samples_per_second": 346.509,
56
- "eval_steps_per_second": 43.409,
57
  "step": 341
58
  },
59
  {
60
  "epoch": 4.989751098096632,
61
  "eval_accuracy": 0.991941391941392,
62
- "eval_f1": 0.9919569277165429,
63
- "eval_loss": 0.04387320205569267,
64
- "eval_precision": 0.9920048531706146,
65
- "eval_recall": 0.991941391941392,
66
- "eval_runtime": 4.0115,
67
- "eval_samples_per_second": 340.268,
68
- "eval_steps_per_second": 42.627,
69
  "step": 426
70
  }
71
  ],
72
  "logging_steps": 500,
73
- "max_steps": 595,
74
  "num_input_tokens_seen": 0,
75
- "num_train_epochs": 7,
76
  "save_steps": 500,
77
  "stateful_callbacks": {
78
  "EarlyStoppingCallback": {
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
 
 
 
18
  "step": 85
19
  },
20
  {
21
  "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
 
 
 
27
  "step": 170
28
  },
29
  {
30
  "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
 
 
 
36
  "step": 256
37
  },
38
  {
39
  "epoch": 3.994143484626647,
40
+ "eval_accuracy": 0.9897435897435898,
41
+ "eval_loss": 0.04228556528687477,
42
+ "eval_runtime": 15.2931,
43
+ "eval_samples_per_second": 89.256,
44
+ "eval_steps_per_second": 11.181,
 
 
 
45
  "step": 341
46
  },
47
  {
48
  "epoch": 4.989751098096632,
49
  "eval_accuracy": 0.991941391941392,
50
+ "eval_loss": 0.044283464550971985,
51
+ "eval_runtime": 15.5546,
52
+ "eval_samples_per_second": 87.756,
53
+ "eval_steps_per_second": 10.994,
 
 
 
54
  "step": 426
55
  }
56
  ],
57
  "logging_steps": 500,
58
+ "max_steps": 850,
59
  "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 10,
61
  "save_steps": 500,
62
  "stateful_callbacks": {
63
  "EarlyStoppingCallback": {
checkpoint-426/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa3df7f2810faa9c35a46d178b12337edb0b134aa27dc1689b302d9bcc9d3d0
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
  size 5240
checkpoint-512/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6beddb5fef4d20200cfcf763c9460267deb7ad4514b1fa760fa4f89d398502cf
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc7074a340619ed7e6d2c55347500f679c4e5f5a30b51392562feb760a9f1c7
3
  size 94763496
checkpoint-512/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cfb7299eb13d9980cb44dcbfcf90cc3e4a95d2c84fd840b959005ca0b7566d6
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b1c42643e3e59059b3734bb2a70cedcdb1a3f2b1cfd13f8b4f6444d7bb6e94
3
  size 189552570
checkpoint-512/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7900f26d6583fa63e5c081f39e0457bc3033e9e087a3f2085f881f9fac700fb3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fe4216d2ecf2b0e2a833d51c97781e3fccf9e2a48a3b58142f2cf031047fa3
3
  size 1064
checkpoint-512/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.991941391941392,
3
- "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-426",
4
  "epoch": 5.997071742313324,
5
  "eval_steps": 500,
6
  "global_step": 512,
@@ -10,88 +10,70 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
- "eval_accuracy": 0.9787545787545787,
14
- "eval_f1": 0.9788275754377449,
15
- "eval_loss": 0.07363971322774887,
16
- "eval_precision": 0.9790028856592324,
17
- "eval_recall": 0.9787545787545787,
18
- "eval_runtime": 4.1234,
19
- "eval_samples_per_second": 331.041,
20
- "eval_steps_per_second": 41.471,
21
  "step": 85
22
  },
23
  {
24
  "epoch": 1.9912152269399708,
25
- "eval_accuracy": 0.9758241758241758,
26
- "eval_f1": 0.9760458977669253,
27
- "eval_loss": 0.0680176243185997,
28
- "eval_precision": 0.9770364666252971,
29
- "eval_recall": 0.9758241758241758,
30
- "eval_runtime": 3.9805,
31
- "eval_samples_per_second": 342.924,
32
- "eval_steps_per_second": 42.96,
33
  "step": 170
34
  },
35
  {
36
  "epoch": 2.998535871156662,
37
- "eval_accuracy": 0.9875457875457876,
38
- "eval_f1": 0.987550637300988,
39
- "eval_loss": 0.044689420610666275,
40
- "eval_precision": 0.9875567820840008,
41
- "eval_recall": 0.9875457875457876,
42
- "eval_runtime": 4.1011,
43
- "eval_samples_per_second": 332.839,
44
- "eval_steps_per_second": 41.696,
45
  "step": 256
46
  },
47
  {
48
  "epoch": 3.994143484626647,
49
- "eval_accuracy": 0.9904761904761905,
50
- "eval_f1": 0.9904945509377323,
51
- "eval_loss": 0.045228052884340286,
52
- "eval_precision": 0.9905452314533213,
53
- "eval_recall": 0.9904761904761905,
54
- "eval_runtime": 3.9393,
55
- "eval_samples_per_second": 346.509,
56
- "eval_steps_per_second": 43.409,
57
  "step": 341
58
  },
59
  {
60
  "epoch": 4.989751098096632,
61
  "eval_accuracy": 0.991941391941392,
62
- "eval_f1": 0.9919569277165429,
63
- "eval_loss": 0.04387320205569267,
64
- "eval_precision": 0.9920048531706146,
65
- "eval_recall": 0.991941391941392,
66
- "eval_runtime": 4.0115,
67
- "eval_samples_per_second": 340.268,
68
- "eval_steps_per_second": 42.627,
69
  "step": 426
70
  },
71
  {
72
  "epoch": 5.856515373352855,
73
- "grad_norm": 0.01621050015091896,
74
- "learning_rate": 6.1795711069424666e-06,
75
- "loss": 0.053,
76
  "step": 500
77
  },
78
  {
79
  "epoch": 5.997071742313324,
80
- "eval_accuracy": 0.991941391941392,
81
- "eval_f1": 0.9919507596926951,
82
- "eval_loss": 0.04010434448719025,
83
- "eval_precision": 0.991971823048746,
84
- "eval_recall": 0.991941391941392,
85
- "eval_runtime": 4.1768,
86
- "eval_samples_per_second": 326.803,
87
- "eval_steps_per_second": 40.94,
88
  "step": 512
89
  }
90
  ],
91
  "logging_steps": 500,
92
- "max_steps": 595,
93
  "num_input_tokens_seen": 0,
94
- "num_train_epochs": 7,
95
  "save_steps": 500,
96
  "stateful_callbacks": {
97
  "EarlyStoppingCallback": {
 
1
  {
2
+ "best_metric": 0.9926739926739927,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
4
  "epoch": 5.997071742313324,
5
  "eval_steps": 500,
6
  "global_step": 512,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
 
 
 
18
  "step": 85
19
  },
20
  {
21
  "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
 
 
 
27
  "step": 170
28
  },
29
  {
30
  "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
 
 
 
36
  "step": 256
37
  },
38
  {
39
  "epoch": 3.994143484626647,
40
+ "eval_accuracy": 0.9897435897435898,
41
+ "eval_loss": 0.04228556528687477,
42
+ "eval_runtime": 15.2931,
43
+ "eval_samples_per_second": 89.256,
44
+ "eval_steps_per_second": 11.181,
 
 
 
45
  "step": 341
46
  },
47
  {
48
  "epoch": 4.989751098096632,
49
  "eval_accuracy": 0.991941391941392,
50
+ "eval_loss": 0.044283464550971985,
51
+ "eval_runtime": 15.5546,
52
+ "eval_samples_per_second": 87.756,
53
+ "eval_steps_per_second": 10.994,
 
 
 
54
  "step": 426
55
  },
56
  {
57
  "epoch": 5.856515373352855,
58
+ "grad_norm": 0.008579956367611885,
59
+ "learning_rate": 3.639014166001028e-05,
60
+ "loss": 0.055,
61
  "step": 500
62
  },
63
  {
64
  "epoch": 5.997071742313324,
65
+ "eval_accuracy": 0.9926739926739927,
66
+ "eval_loss": 0.04338795691728592,
67
+ "eval_runtime": 15.1048,
68
+ "eval_samples_per_second": 90.369,
69
+ "eval_steps_per_second": 11.321,
 
 
 
70
  "step": 512
71
  }
72
  ],
73
  "logging_steps": 500,
74
+ "max_steps": 850,
75
  "num_input_tokens_seen": 0,
76
+ "num_train_epochs": 10,
77
  "save_steps": 500,
78
  "stateful_callbacks": {
79
  "EarlyStoppingCallback": {
checkpoint-512/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa3df7f2810faa9c35a46d178b12337edb0b134aa27dc1689b302d9bcc9d3d0
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
  size 5240
checkpoint-597/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-597/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15156ce7496feffe08a94b0b76ed04e2398b912b56dfe3d329336cae4f32b8ab
3
+ size 94763496
checkpoint-597/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a1d6ff155620819b854ea259f85accf2532818e85d714ea4a614a3b91d42cb
3
+ size 189552570
checkpoint-597/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9faf0d148cc716f365ebe8d8995bc864d6ff1310fd1b0cf0abdbc5a6b27134
3
+ size 14308
checkpoint-597/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08eb49f7720b737aa4a97dd1c15d069bd20c33dc2f3de8105e499906c629b0bb
3
+ size 1064
checkpoint-597/trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9926739926739927,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
4
+ "epoch": 6.992679355783309,
5
+ "eval_steps": 500,
6
+ "global_step": 597,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
18
+ "step": 85
19
+ },
20
+ {
21
+ "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
27
+ "step": 170
28
+ },
29
+ {
30
+ "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
36
+ "step": 256
37
+ },
38
+ {
39
+ "epoch": 3.994143484626647,
40
+ "eval_accuracy": 0.9897435897435898,
41
+ "eval_loss": 0.04228556528687477,
42
+ "eval_runtime": 15.2931,
43
+ "eval_samples_per_second": 89.256,
44
+ "eval_steps_per_second": 11.181,
45
+ "step": 341
46
+ },
47
+ {
48
+ "epoch": 4.989751098096632,
49
+ "eval_accuracy": 0.991941391941392,
50
+ "eval_loss": 0.044283464550971985,
51
+ "eval_runtime": 15.5546,
52
+ "eval_samples_per_second": 87.756,
53
+ "eval_steps_per_second": 10.994,
54
+ "step": 426
55
+ },
56
+ {
57
+ "epoch": 5.856515373352855,
58
+ "grad_norm": 0.008579956367611885,
59
+ "learning_rate": 3.639014166001028e-05,
60
+ "loss": 0.055,
61
+ "step": 500
62
+ },
63
+ {
64
+ "epoch": 5.997071742313324,
65
+ "eval_accuracy": 0.9926739926739927,
66
+ "eval_loss": 0.04338795691728592,
67
+ "eval_runtime": 15.1048,
68
+ "eval_samples_per_second": 90.369,
69
+ "eval_steps_per_second": 11.321,
70
+ "step": 512
71
+ },
72
+ {
73
+ "epoch": 6.992679355783309,
74
+ "eval_accuracy": 0.9926739926739927,
75
+ "eval_loss": 0.04399614781141281,
76
+ "eval_runtime": 15.222,
77
+ "eval_samples_per_second": 89.673,
78
+ "eval_steps_per_second": 11.234,
79
+ "step": 597
80
+ }
81
+ ],
82
+ "logging_steps": 500,
83
+ "max_steps": 850,
84
+ "num_input_tokens_seen": 0,
85
+ "num_train_epochs": 10,
86
+ "save_steps": 500,
87
+ "stateful_callbacks": {
88
+ "EarlyStoppingCallback": {
89
+ "args": {
90
+ "early_stopping_patience": 3,
91
+ "early_stopping_threshold": 0.0
92
+ },
93
+ "attributes": {
94
+ "early_stopping_patience_counter": 0
95
+ }
96
+ },
97
+ "TrainerControl": {
98
+ "args": {
99
+ "should_epoch_stop": false,
100
+ "should_evaluate": false,
101
+ "should_log": false,
102
+ "should_save": true,
103
+ "should_training_stop": false
104
+ },
105
+ "attributes": {}
106
+ }
107
+ },
108
+ "total_flos": 8.691905319552e+16,
109
+ "train_batch_size": 8,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
checkpoint-597/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
+ size 5240
checkpoint-683/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-683/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ec3a122dd4e1c3f5b4ae3dc2e2256f512a563d42eb82426ac3f8094e0c4490
3
+ size 94763496
checkpoint-683/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6591188ba0c4025fcbff86219e7c2755b85671c8b4d10202fa03cef2f8831a1
3
+ size 189552570
checkpoint-683/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a6b5c1026053dbddf0437264821c51fb9b6be038e7765f49aa97ac2f5521f2
3
+ size 14308
checkpoint-683/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b712ee88015e952bb23b1f5495f272411d9c19a17334b27df15dc1ebbac98f35
3
+ size 1064
checkpoint-683/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9926739926739927,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 683,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
18
+ "step": 85
19
+ },
20
+ {
21
+ "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
27
+ "step": 170
28
+ },
29
+ {
30
+ "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
36
+ "step": 256
37
+ },
38
+ {
39
+ "epoch": 3.994143484626647,
40
+ "eval_accuracy": 0.9897435897435898,
41
+ "eval_loss": 0.04228556528687477,
42
+ "eval_runtime": 15.2931,
43
+ "eval_samples_per_second": 89.256,
44
+ "eval_steps_per_second": 11.181,
45
+ "step": 341
46
+ },
47
+ {
48
+ "epoch": 4.989751098096632,
49
+ "eval_accuracy": 0.991941391941392,
50
+ "eval_loss": 0.044283464550971985,
51
+ "eval_runtime": 15.5546,
52
+ "eval_samples_per_second": 87.756,
53
+ "eval_steps_per_second": 10.994,
54
+ "step": 426
55
+ },
56
+ {
57
+ "epoch": 5.856515373352855,
58
+ "grad_norm": 0.008579956367611885,
59
+ "learning_rate": 3.639014166001028e-05,
60
+ "loss": 0.055,
61
+ "step": 500
62
+ },
63
+ {
64
+ "epoch": 5.997071742313324,
65
+ "eval_accuracy": 0.9926739926739927,
66
+ "eval_loss": 0.04338795691728592,
67
+ "eval_runtime": 15.1048,
68
+ "eval_samples_per_second": 90.369,
69
+ "eval_steps_per_second": 11.321,
70
+ "step": 512
71
+ },
72
+ {
73
+ "epoch": 6.992679355783309,
74
+ "eval_accuracy": 0.9926739926739927,
75
+ "eval_loss": 0.04399614781141281,
76
+ "eval_runtime": 15.222,
77
+ "eval_samples_per_second": 89.673,
78
+ "eval_steps_per_second": 11.234,
79
+ "step": 597
80
+ },
81
+ {
82
+ "epoch": 8.0,
83
+ "eval_accuracy": 0.9926739926739927,
84
+ "eval_loss": 0.045955102890729904,
85
+ "eval_runtime": 15.0695,
86
+ "eval_samples_per_second": 90.58,
87
+ "eval_steps_per_second": 11.347,
88
+ "step": 683
89
+ }
90
+ ],
91
+ "logging_steps": 500,
92
+ "max_steps": 850,
93
+ "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 10,
95
+ "save_steps": 500,
96
+ "stateful_callbacks": {
97
+ "EarlyStoppingCallback": {
98
+ "args": {
99
+ "early_stopping_patience": 3,
100
+ "early_stopping_threshold": 0.0
101
+ },
102
+ "attributes": {
103
+ "early_stopping_patience_counter": 0
104
+ }
105
+ },
106
+ "TrainerControl": {
107
+ "args": {
108
+ "should_epoch_stop": false,
109
+ "should_evaluate": false,
110
+ "should_log": false,
111
+ "should_save": true,
112
+ "should_training_stop": false
113
+ },
114
+ "attributes": {}
115
+ }
116
+ },
117
+ "total_flos": 9.933606079488e+16,
118
+ "train_batch_size": 8,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
checkpoint-683/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
+ size 5240
checkpoint-768/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-768/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5671ffc6960b29ad80f820b4317ec548ff0deefca2464ad359c421c360e64f
3
+ size 94763496
checkpoint-768/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7516d91f602bba3efff25344b03b35e85d41b8ce4db2a56619d6dcf6cd2cc2df
3
+ size 189552570
checkpoint-768/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be73eba9bf4e828d2acb6ab02c40fd90fe2c23584b8cf78d262c1f935416d2e6
3
+ size 14308
checkpoint-768/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a9a21b9ea0c395732aadaa7b885d80eaa4d81c9d9d1eea099d6180e939da87
3
+ size 1064
checkpoint-768/trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9926739926739927,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
4
+ "epoch": 8.995607613469986,
5
+ "eval_steps": 500,
6
+ "global_step": 768,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9956076134699854,
13
+ "eval_accuracy": 0.9772893772893773,
14
+ "eval_loss": 0.06922276318073273,
15
+ "eval_runtime": 15.3212,
16
+ "eval_samples_per_second": 89.092,
17
+ "eval_steps_per_second": 11.161,
18
+ "step": 85
19
+ },
20
+ {
21
+ "epoch": 1.9912152269399708,
22
+ "eval_accuracy": 0.9860805860805861,
23
+ "eval_loss": 0.04661192744970322,
24
+ "eval_runtime": 15.611,
25
+ "eval_samples_per_second": 87.438,
26
+ "eval_steps_per_second": 10.954,
27
+ "step": 170
28
+ },
29
+ {
30
+ "epoch": 2.998535871156662,
31
+ "eval_accuracy": 0.9853479853479854,
32
+ "eval_loss": 0.04894961416721344,
33
+ "eval_runtime": 15.1886,
34
+ "eval_samples_per_second": 89.87,
35
+ "eval_steps_per_second": 11.258,
36
+ "step": 256
37
+ },
38
+ {
39
+ "epoch": 3.994143484626647,
40
+ "eval_accuracy": 0.9897435897435898,
41
+ "eval_loss": 0.04228556528687477,
42
+ "eval_runtime": 15.2931,
43
+ "eval_samples_per_second": 89.256,
44
+ "eval_steps_per_second": 11.181,
45
+ "step": 341
46
+ },
47
+ {
48
+ "epoch": 4.989751098096632,
49
+ "eval_accuracy": 0.991941391941392,
50
+ "eval_loss": 0.044283464550971985,
51
+ "eval_runtime": 15.5546,
52
+ "eval_samples_per_second": 87.756,
53
+ "eval_steps_per_second": 10.994,
54
+ "step": 426
55
+ },
56
+ {
57
+ "epoch": 5.856515373352855,
58
+ "grad_norm": 0.008579956367611885,
59
+ "learning_rate": 3.639014166001028e-05,
60
+ "loss": 0.055,
61
+ "step": 500
62
+ },
63
+ {
64
+ "epoch": 5.997071742313324,
65
+ "eval_accuracy": 0.9926739926739927,
66
+ "eval_loss": 0.04338795691728592,
67
+ "eval_runtime": 15.1048,
68
+ "eval_samples_per_second": 90.369,
69
+ "eval_steps_per_second": 11.321,
70
+ "step": 512
71
+ },
72
+ {
73
+ "epoch": 6.992679355783309,
74
+ "eval_accuracy": 0.9926739926739927,
75
+ "eval_loss": 0.04399614781141281,
76
+ "eval_runtime": 15.222,
77
+ "eval_samples_per_second": 89.673,
78
+ "eval_steps_per_second": 11.234,
79
+ "step": 597
80
+ },
81
+ {
82
+ "epoch": 8.0,
83
+ "eval_accuracy": 0.9926739926739927,
84
+ "eval_loss": 0.045955102890729904,
85
+ "eval_runtime": 15.0695,
86
+ "eval_samples_per_second": 90.58,
87
+ "eval_steps_per_second": 11.347,
88
+ "step": 683
89
+ },
90
+ {
91
+ "epoch": 8.995607613469986,
92
+ "eval_accuracy": 0.9926739926739927,
93
+ "eval_loss": 0.04587433487176895,
94
+ "eval_runtime": 15.048,
95
+ "eval_samples_per_second": 90.71,
96
+ "eval_steps_per_second": 11.364,
97
+ "step": 768
98
+ }
99
+ ],
100
+ "logging_steps": 500,
101
+ "max_steps": 850,
102
+ "num_input_tokens_seen": 0,
103
+ "num_train_epochs": 10,
104
+ "save_steps": 500,
105
+ "stateful_callbacks": {
106
+ "EarlyStoppingCallback": {
107
+ "args": {
108
+ "early_stopping_patience": 3,
109
+ "early_stopping_threshold": 0.0
110
+ },
111
+ "attributes": {
112
+ "early_stopping_patience_counter": 0
113
+ }
114
+ },
115
+ "TrainerControl": {
116
+ "args": {
117
+ "should_epoch_stop": false,
118
+ "should_evaluate": false,
119
+ "should_log": false,
120
+ "should_save": true,
121
+ "should_training_stop": true
122
+ },
123
+ "attributes": {}
124
+ }
125
+ },
126
+ "total_flos": 1.1175306839424e+17,
127
+ "train_batch_size": 8,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
checkpoint-768/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08b4365c154a27d61d8cdfad62c4717bf003430323e6c3916f01c3121d721
3
+ size 5240
checkpoint-85/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:687e267a3c37d18cce5591d5301b06a4193f540a3ed0c054e9913e5e610aef05
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9779c7119f4a2210495b9b5237a5030e7c0eddabdde1b1ca2c8239a751959e1
3
  size 94763496
checkpoint-85/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ff974afccdd073da4ec78806e9470c99c469ae8a871771439016949486039a9
3
  size 189552570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6690ddab61f45db23b28120bb5c39be4f9a152f1c88b3ae432902f89efc452
3
  size 189552570
checkpoint-85/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daf90af7d8b581c8b4882d01681a4f4fb886f79b4c5624a5d256aba635f56702
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324ecccddc3afacd1a2ab429e35f5e62f986b75e609998929bd8ab5fcbb2e6a7
3
  size 1064