Hugging Face's logo

A-POR-LOS-8000
/
distilhubert-finetuned-mixed-data

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Marcos12886 commited on
Commit
b73f096
•
1 Parent(s): c9c4a3f

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 +28 -32
  2. checkpoint-121/model.safetensors +1 -1
  3. checkpoint-121/optimizer.pt +1 -1
  4. checkpoint-121/scheduler.pt +1 -1
  5. checkpoint-121/trainer_state.json +43 -43
  6. checkpoint-121/training_args.bin +1 -1
  7. checkpoint-145/config.json +85 -0
  8. checkpoint-145/model.safetensors +3 -0
  9. checkpoint-145/optimizer.pt +3 -0
  10. checkpoint-145/rng_state.pth +3 -0
  11. checkpoint-145/scheduler.pt +3 -0
  12. checkpoint-145/trainer_state.json +114 -0
  13. checkpoint-145/training_args.bin +3 -0
  14. checkpoint-169/config.json +85 -0
  15. checkpoint-169/model.safetensors +3 -0
  16. checkpoint-169/optimizer.pt +3 -0
  17. checkpoint-169/rng_state.pth +3 -0
  18. checkpoint-169/scheduler.pt +3 -0
  19. checkpoint-169/trainer_state.json +126 -0
  20. checkpoint-169/training_args.bin +3 -0
  21. checkpoint-194/config.json +85 -0
  22. checkpoint-194/model.safetensors +3 -0
  23. checkpoint-194/optimizer.pt +3 -0
  24. checkpoint-194/rng_state.pth +3 -0
  25. checkpoint-194/scheduler.pt +3 -0
  26. checkpoint-194/trainer_state.json +138 -0
  27. checkpoint-194/training_args.bin +3 -0
  28. checkpoint-218/config.json +85 -0
  29. checkpoint-218/model.safetensors +3 -0
  30. checkpoint-218/optimizer.pt +3 -0
  31. checkpoint-218/rng_state.pth +3 -0
  32. checkpoint-218/scheduler.pt +3 -0
  33. checkpoint-218/trainer_state.json +150 -0
  34. checkpoint-218/training_args.bin +3 -0
  35. checkpoint-24/model.safetensors +1 -1
  36. checkpoint-24/optimizer.pt +1 -1
  37. checkpoint-24/rng_state.pth +1 -1
  38. checkpoint-24/scheduler.pt +1 -1
  39. checkpoint-24/trainer_state.json +13 -13
  40. checkpoint-24/training_args.bin +1 -1
  41. checkpoint-242/config.json +85 -0
  42. checkpoint-242/model.safetensors +3 -0
  43. checkpoint-242/optimizer.pt +3 -0
  44. checkpoint-242/rng_state.pth +3 -0
  45. checkpoint-242/scheduler.pt +3 -0
  46. checkpoint-242/trainer_state.json +162 -0
  47. checkpoint-242/training_args.bin +3 -0
  48. checkpoint-266/config.json +85 -0
  49. checkpoint-266/model.safetensors +3 -0
  50. checkpoint-266/optimizer.pt +3 -0
README.md CHANGED
@@ -4,26 +4,14 @@ license: apache-2.0
4
  base_model: ntu-spml/distilhubert
5
  tags:
6
  - generated_from_trainer
7
- datasets:
8
- - audiofolder
9
  metrics:
10
  - accuracy
 
 
 
11
  model-index:
12
  - name: distilhubert-finetuned-mixed-data
13
- results:
14
- - task:
15
- name: Audio Classification
16
- type: audio-classification
17
- dataset:
18
- name: audiofolder
19
- type: audiofolder
20
- config: default
21
- split: train
22
- args: default
23
- metrics:
24
- - name: Accuracy
25
- type: accuracy
26
- value: 0.8691275167785235
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # distilhubert-finetuned-mixed-data
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: 0.3360
37
- - Accuracy: 0.8691
 
 
 
38
 
39
  ## Model description
40
 
@@ -61,25 +52,30 @@ The following hyperparameters were used during training:
61
  - total_train_batch_size: 64
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: 7
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:------:|:----:|:---------------:|:--------:|
71
- | No log | 0.9664 | 18 | 0.6860 | 0.7584 |
72
- | No log | 1.9866 | 37 | 0.4623 | 0.8020 |
73
- | No log | 2.9530 | 55 | 0.4069 | 0.8188 |
74
- | No log | 3.9732 | 74 | 0.3811 | 0.8356 |
75
- | No log | 4.9933 | 93 | 0.3542 | 0.8356 |
76
- | No log | 5.9597 | 111 | 0.3380 | 0.8658 |
77
- | No log | 6.7651 | 126 | 0.3360 | 0.8691 |
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.44.2
83
- - Pytorch 2.4.0+cu121
84
- - Datasets 2.21.0
85
  - Tokenizers 0.19.1
 
4
  base_model: ntu-spml/distilhubert
5
  tags:
6
  - generated_from_trainer
 
 
7
  metrics:
8
  - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
  model-index:
13
  - name: distilhubert-finetuned-mixed-data
14
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
19
 
20
  # distilhubert-finetuned-mixed-data
21
 
22
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.4765
25
+ - Accuracy: 0.8475
26
+ - Precision: 0.8497
27
+ - Recall: 0.8475
28
+ - F1: 0.8484
29
 
30
  ## Model description
31
 
 
52
  - total_train_batch_size: 64
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
+ - lr_scheduler_warmup_ratio: 0.01
56
+ - num_epochs: 15
57
 
58
  ### Training results
59
 
60
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
+ | No log | 0.9897 | 24 | 0.9809 | 0.6357 | 0.5920 | 0.6357 | 0.5921 |
63
+ | No log | 1.9794 | 48 | 0.7444 | 0.7158 | 0.6992 | 0.7158 | 0.6905 |
64
+ | No log | 2.9691 | 72 | 0.6172 | 0.7494 | 0.7438 | 0.7494 | 0.7449 |
65
+ | No log | 4.0 | 97 | 0.5431 | 0.7984 | 0.7918 | 0.7984 | 0.7874 |
66
+ | No log | 4.9897 | 121 | 0.5269 | 0.8010 | 0.8006 | 0.8010 | 0.7975 |
67
+ | No log | 5.9794 | 145 | 0.5811 | 0.7494 | 0.7802 | 0.7494 | 0.7551 |
68
+ | No log | 6.9691 | 169 | 0.4408 | 0.8398 | 0.8366 | 0.8398 | 0.8355 |
69
+ | No log | 8.0 | 194 | 0.4687 | 0.8191 | 0.8188 | 0.8191 | 0.8168 |
70
+ | No log | 8.9897 | 218 | 0.4364 | 0.8475 | 0.8483 | 0.8475 | 0.8474 |
71
+ | No log | 9.9794 | 242 | 0.4291 | 0.8579 | 0.8561 | 0.8579 | 0.8568 |
72
+ | No log | 10.9691 | 266 | 0.4699 | 0.8501 | 0.8582 | 0.8501 | 0.8528 |
73
+ | No log | 12.0 | 291 | 0.4862 | 0.8450 | 0.8536 | 0.8450 | 0.8480 |
74
+ | No log | 12.9897 | 315 | 0.4765 | 0.8475 | 0.8497 | 0.8475 | 0.8484 |
75
 
76
 
77
  ### Framework versions
78
 
79
  - Transformers 4.44.2
80
+ - Pytorch 2.4.1+cu121
 
81
  - Tokenizers 0.19.1
checkpoint-121/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f17cc1a80f9cdf7f1c5c94c70062ca59ee73223709355f94eae716447e99d02
3
  size 94765560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61738703583616f26bc5974045f101b4badf661cb1bd5759b55ffedbf42f8309
3
  size 94765560
checkpoint-121/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af430e7b5cbd26cc609cc5c918049ec696a387c13101b4292d1bd68dd2695f0e
3
  size 189556666
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04d7aa37706181567dea5d9c17d0a79ae70a3f43b546fd604def5a5c896f325
3
  size 189556666
checkpoint-121/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:192b51d0f1e5456c85d7a6eeae550a33132f97495282fa7f439444f5f22297cf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4a0a93ff2c02ad8dfec37403a0eff289573d406127ab0a60fb4386bc8bcb2b
3
  size 1064
checkpoint-121/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7648578811369509,
3
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121",
4
  "epoch": 4.989690721649485,
5
  "eval_steps": 500,
@@ -10,69 +10,69 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9896907216494846,
13
- "eval_accuracy": 0.6098191214470284,
14
- "eval_f1": 0.5527821682108387,
15
- "eval_loss": 1.0193405151367188,
16
- "eval_precision": 0.7003292379638224,
17
- "eval_recall": 0.6098191214470284,
18
- "eval_runtime": 1.7319,
19
- "eval_samples_per_second": 223.453,
20
- "eval_steps_per_second": 28.293,
21
  "step": 24
22
  },
23
  {
24
  "epoch": 1.9793814432989691,
25
- "eval_accuracy": 0.6795865633074936,
26
- "eval_f1": 0.6650515718181741,
27
- "eval_loss": 0.7780925631523132,
28
- "eval_precision": 0.6877908327609833,
29
- "eval_recall": 0.6795865633074936,
30
- "eval_runtime": 1.7105,
31
- "eval_samples_per_second": 226.247,
32
- "eval_steps_per_second": 28.646,
33
  "step": 48
34
  },
35
  {
36
  "epoch": 2.9690721649484537,
37
- "eval_accuracy": 0.7260981912144703,
38
- "eval_f1": 0.7125387559196679,
39
- "eval_loss": 0.663092315196991,
40
- "eval_precision": 0.7236217153897081,
41
- "eval_recall": 0.7260981912144703,
42
- "eval_runtime": 1.7131,
43
- "eval_samples_per_second": 225.911,
44
- "eval_steps_per_second": 28.604,
45
  "step": 72
46
  },
47
  {
48
  "epoch": 4.0,
49
- "eval_accuracy": 0.7493540051679587,
50
- "eval_f1": 0.7323843170610034,
51
- "eval_loss": 0.5870956778526306,
52
- "eval_precision": 0.7505520883603423,
53
- "eval_recall": 0.7493540051679587,
54
- "eval_runtime": 1.7332,
55
- "eval_samples_per_second": 223.293,
56
- "eval_steps_per_second": 28.272,
57
  "step": 97
58
  },
59
  {
60
  "epoch": 4.989690721649485,
61
- "eval_accuracy": 0.7648578811369509,
62
- "eval_f1": 0.7570271532827265,
63
- "eval_loss": 0.5548774003982544,
64
- "eval_precision": 0.7717080207133444,
65
- "eval_recall": 0.7648578811369509,
66
- "eval_runtime": 1.744,
67
- "eval_samples_per_second": 221.907,
68
- "eval_steps_per_second": 28.097,
69
  "step": 121
70
  }
71
  ],
72
  "logging_steps": 500,
73
- "max_steps": 144,
74
  "num_input_tokens_seen": 0,
75
- "num_train_epochs": 6,
76
  "save_steps": 500,
77
  "stateful_callbacks": {
78
  "EarlyStoppingCallback": {
 
1
  {
2
+ "best_metric": 0.8010335917312662,
3
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121",
4
  "epoch": 4.989690721649485,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
  "step": 24
22
  },
23
  {
24
  "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.7157622739018088,
26
+ "eval_f1": 0.6905410405322238,
27
+ "eval_loss": 0.7444477081298828,
28
+ "eval_precision": 0.6992377248989063,
29
+ "eval_recall": 0.7157622739018088,
30
+ "eval_runtime": 1.6941,
31
+ "eval_samples_per_second": 228.443,
32
+ "eval_steps_per_second": 28.924,
33
  "step": 48
34
  },
35
  {
36
  "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7493540051679587,
38
+ "eval_f1": 0.744898505571463,
39
+ "eval_loss": 0.6171658039093018,
40
+ "eval_precision": 0.7437592422989429,
41
+ "eval_recall": 0.7493540051679587,
42
+ "eval_runtime": 1.6943,
43
+ "eval_samples_per_second": 228.408,
44
+ "eval_steps_per_second": 28.92,
45
  "step": 72
46
  },
47
  {
48
  "epoch": 4.0,
49
+ "eval_accuracy": 0.7984496124031008,
50
+ "eval_f1": 0.7873621619744228,
51
+ "eval_loss": 0.5430988073348999,
52
+ "eval_precision": 0.79180344284319,
53
+ "eval_recall": 0.7984496124031008,
54
+ "eval_runtime": 1.7027,
55
+ "eval_samples_per_second": 227.289,
56
+ "eval_steps_per_second": 28.778,
57
  "step": 97
58
  },
59
  {
60
  "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.8010335917312662,
62
+ "eval_f1": 0.7974946178390901,
63
+ "eval_loss": 0.5268548130989075,
64
+ "eval_precision": 0.8005965453214461,
65
+ "eval_recall": 0.8010335917312662,
66
+ "eval_runtime": 1.6829,
67
+ "eval_samples_per_second": 229.957,
68
+ "eval_steps_per_second": 29.116,
69
  "step": 121
70
  }
71
  ],
72
  "logging_steps": 500,
73
+ "max_steps": 360,
74
  "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 15,
76
  "save_steps": 500,
77
  "stateful_callbacks": {
78
  "EarlyStoppingCallback": {
checkpoint-121/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f758b94689e09a814f1948cbbce56e483b2b53509b111e749d1961a9e2d3ad45
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
  size 5240
checkpoint-145/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-145/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b1cac8d8be6152086485540750316f43a58660bddd11c298bb50d0f3f5f531
3
+ size 94765560
checkpoint-145/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74fa4c7ca2e76ec752e5b913444b39e61cef0b5760afb453b5c55805b47cacc
3
+ size 189556666
checkpoint-145/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0867bb3588983088e1ae19ae31c54b18cd181442273a375c356a0362c53a9a5
3
+ size 14308
checkpoint-145/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e2160d5bd28532b533e3efabec8ccad052eb12401ff324f1c912ac3e74c929
3
+ size 1064
checkpoint-145/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8010335917312662,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121",
4
+ "epoch": 5.979381443298969,
5
+ "eval_steps": 500,
6
+ "global_step": 145,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.7157622739018088,
26
+ "eval_f1": 0.6905410405322238,
27
+ "eval_loss": 0.7444477081298828,
28
+ "eval_precision": 0.6992377248989063,
29
+ "eval_recall": 0.7157622739018088,
30
+ "eval_runtime": 1.6941,
31
+ "eval_samples_per_second": 228.443,
32
+ "eval_steps_per_second": 28.924,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7493540051679587,
38
+ "eval_f1": 0.744898505571463,
39
+ "eval_loss": 0.6171658039093018,
40
+ "eval_precision": 0.7437592422989429,
41
+ "eval_recall": 0.7493540051679587,
42
+ "eval_runtime": 1.6943,
43
+ "eval_samples_per_second": 228.408,
44
+ "eval_steps_per_second": 28.92,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7984496124031008,
50
+ "eval_f1": 0.7873621619744228,
51
+ "eval_loss": 0.5430988073348999,
52
+ "eval_precision": 0.79180344284319,
53
+ "eval_recall": 0.7984496124031008,
54
+ "eval_runtime": 1.7027,
55
+ "eval_samples_per_second": 227.289,
56
+ "eval_steps_per_second": 28.778,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.8010335917312662,
62
+ "eval_f1": 0.7974946178390901,
63
+ "eval_loss": 0.5268548130989075,
64
+ "eval_precision": 0.8005965453214461,
65
+ "eval_recall": 0.8010335917312662,
66
+ "eval_runtime": 1.6829,
67
+ "eval_samples_per_second": 229.957,
68
+ "eval_steps_per_second": 29.116,
69
+ "step": 121
70
+ },
71
+ {
72
+ "epoch": 5.979381443298969,
73
+ "eval_accuracy": 0.7493540051679587,
74
+ "eval_f1": 0.7551329793037762,
75
+ "eval_loss": 0.5810549259185791,
76
+ "eval_precision": 0.7802262423287315,
77
+ "eval_recall": 0.7493540051679587,
78
+ "eval_runtime": 1.6999,
79
+ "eval_samples_per_second": 227.658,
80
+ "eval_steps_per_second": 28.825,
81
+ "step": 145
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 360,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 15,
88
+ "save_steps": 500,
89
+ "stateful_callbacks": {
90
+ "EarlyStoppingCallback": {
91
+ "args": {
92
+ "early_stopping_patience": 3,
93
+ "early_stopping_threshold": 0.0
94
+ },
95
+ "attributes": {
96
+ "early_stopping_patience_counter": 0
97
+ }
98
+ },
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": false
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 2.10820802112e+16,
111
+ "train_batch_size": 8,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-145/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
+ size 5240
checkpoint-169/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-169/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052c2fac14563eb5b0b53eb4a3f6509d46dcf61f99ea7c0e5e76df5345230eff
3
+ size 94765560
checkpoint-169/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672db33956055547a36f8f888cdb0f8124de62210906cbe58b87898baf646fe9
3
+ size 189556666
checkpoint-169/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d85d4b435d4ac4552bb46f32d5f63a55dbc65baaa5af6a14b6b39e968f4b8e
3
+ size 14308
checkpoint-169/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a897dacc1b915150336aff74c1f17b3b8504d76168703307724c32fe3bca6896
3
+ size 1064
checkpoint-169/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8397932816537468,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-169",
4
+ "epoch": 6.969072164948454,
5
+ "eval_steps": 500,
6
+ "global_step": 169,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.7157622739018088,
26
+ "eval_f1": 0.6905410405322238,
27
+ "eval_loss": 0.7444477081298828,
28
+ "eval_precision": 0.6992377248989063,
29
+ "eval_recall": 0.7157622739018088,
30
+ "eval_runtime": 1.6941,
31
+ "eval_samples_per_second": 228.443,
32
+ "eval_steps_per_second": 28.924,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7493540051679587,
38
+ "eval_f1": 0.744898505571463,
39
+ "eval_loss": 0.6171658039093018,
40
+ "eval_precision": 0.7437592422989429,
41
+ "eval_recall": 0.7493540051679587,
42
+ "eval_runtime": 1.6943,
43
+ "eval_samples_per_second": 228.408,
44
+ "eval_steps_per_second": 28.92,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7984496124031008,
50
+ "eval_f1": 0.7873621619744228,
51
+ "eval_loss": 0.5430988073348999,
52
+ "eval_precision": 0.79180344284319,
53
+ "eval_recall": 0.7984496124031008,
54
+ "eval_runtime": 1.7027,
55
+ "eval_samples_per_second": 227.289,
56
+ "eval_steps_per_second": 28.778,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.8010335917312662,
62
+ "eval_f1": 0.7974946178390901,
63
+ "eval_loss": 0.5268548130989075,
64
+ "eval_precision": 0.8005965453214461,
65
+ "eval_recall": 0.8010335917312662,
66
+ "eval_runtime": 1.6829,
67
+ "eval_samples_per_second": 229.957,
68
+ "eval_steps_per_second": 29.116,
69
+ "step": 121
70
+ },
71
+ {
72
+ "epoch": 5.979381443298969,
73
+ "eval_accuracy": 0.7493540051679587,
74
+ "eval_f1": 0.7551329793037762,
75
+ "eval_loss": 0.5810549259185791,
76
+ "eval_precision": 0.7802262423287315,
77
+ "eval_recall": 0.7493540051679587,
78
+ "eval_runtime": 1.6999,
79
+ "eval_samples_per_second": 227.658,
80
+ "eval_steps_per_second": 28.825,
81
+ "step": 145
82
+ },
83
+ {
84
+ "epoch": 6.969072164948454,
85
+ "eval_accuracy": 0.8397932816537468,
86
+ "eval_f1": 0.8354840008265724,
87
+ "eval_loss": 0.44080850481987,
88
+ "eval_precision": 0.8365717854569443,
89
+ "eval_recall": 0.8397932816537468,
90
+ "eval_runtime": 1.6785,
91
+ "eval_samples_per_second": 230.56,
92
+ "eval_steps_per_second": 29.192,
93
+ "step": 169
94
+ }
95
+ ],
96
+ "logging_steps": 500,
97
+ "max_steps": 360,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 15,
100
+ "save_steps": 500,
101
+ "stateful_callbacks": {
102
+ "EarlyStoppingCallback": {
103
+ "args": {
104
+ "early_stopping_patience": 3,
105
+ "early_stopping_threshold": 0.0
106
+ },
107
+ "attributes": {
108
+ "early_stopping_patience_counter": 0
109
+ }
110
+ },
111
+ "TrainerControl": {
112
+ "args": {
113
+ "should_epoch_stop": false,
114
+ "should_evaluate": false,
115
+ "should_log": false,
116
+ "should_save": true,
117
+ "should_training_stop": false
118
+ },
119
+ "attributes": {}
120
+ }
121
+ },
122
+ "total_flos": 2.45957602464e+16,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
checkpoint-169/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
+ size 5240
checkpoint-194/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-194/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03ee65315496952ebb447ef8a2d41c18b1e5e1649887b43e9d670daab42cd79
3
+ size 94765560
checkpoint-194/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b9a71b29339ce815e0272ac73c5e9382e8e4b94e000d00c2c15c46fcaf1bb1
3
+ size 189556666
checkpoint-194/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a98371a8e546887d8a0cf63952365049758fe889acd42fc72eb734ef3af0332
3
+ size 14308
checkpoint-194/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf3f9f9e1b079187c143133062b7476177d05ae3b26e39797b7b8deffda481f
3
+ size 1064
checkpoint-194/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8397932816537468,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-169",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 194,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.7157622739018088,
26
+ "eval_f1": 0.6905410405322238,
27
+ "eval_loss": 0.7444477081298828,
28
+ "eval_precision": 0.6992377248989063,
29
+ "eval_recall": 0.7157622739018088,
30
+ "eval_runtime": 1.6941,
31
+ "eval_samples_per_second": 228.443,
32
+ "eval_steps_per_second": 28.924,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7493540051679587,
38
+ "eval_f1": 0.744898505571463,
39
+ "eval_loss": 0.6171658039093018,
40
+ "eval_precision": 0.7437592422989429,
41
+ "eval_recall": 0.7493540051679587,
42
+ "eval_runtime": 1.6943,
43
+ "eval_samples_per_second": 228.408,
44
+ "eval_steps_per_second": 28.92,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7984496124031008,
50
+ "eval_f1": 0.7873621619744228,
51
+ "eval_loss": 0.5430988073348999,
52
+ "eval_precision": 0.79180344284319,
53
+ "eval_recall": 0.7984496124031008,
54
+ "eval_runtime": 1.7027,
55
+ "eval_samples_per_second": 227.289,
56
+ "eval_steps_per_second": 28.778,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.8010335917312662,
62
+ "eval_f1": 0.7974946178390901,
63
+ "eval_loss": 0.5268548130989075,
64
+ "eval_precision": 0.8005965453214461,
65
+ "eval_recall": 0.8010335917312662,
66
+ "eval_runtime": 1.6829,
67
+ "eval_samples_per_second": 229.957,
68
+ "eval_steps_per_second": 29.116,
69
+ "step": 121
70
+ },
71
+ {
72
+ "epoch": 5.979381443298969,
73
+ "eval_accuracy": 0.7493540051679587,
74
+ "eval_f1": 0.7551329793037762,
75
+ "eval_loss": 0.5810549259185791,
76
+ "eval_precision": 0.7802262423287315,
77
+ "eval_recall": 0.7493540051679587,
78
+ "eval_runtime": 1.6999,
79
+ "eval_samples_per_second": 227.658,
80
+ "eval_steps_per_second": 28.825,
81
+ "step": 145
82
+ },
83
+ {
84
+ "epoch": 6.969072164948454,
85
+ "eval_accuracy": 0.8397932816537468,
86
+ "eval_f1": 0.8354840008265724,
87
+ "eval_loss": 0.44080850481987,
88
+ "eval_precision": 0.8365717854569443,
89
+ "eval_recall": 0.8397932816537468,
90
+ "eval_runtime": 1.6785,
91
+ "eval_samples_per_second": 230.56,
92
+ "eval_steps_per_second": 29.192,
93
+ "step": 169
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8191214470284238,
98
+ "eval_f1": 0.8167837576120855,
99
+ "eval_loss": 0.46871018409729004,
100
+ "eval_precision": 0.8187643627479353,
101
+ "eval_recall": 0.8191214470284238,
102
+ "eval_runtime": 1.6719,
103
+ "eval_samples_per_second": 231.477,
104
+ "eval_steps_per_second": 29.308,
105
+ "step": 194
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 360,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 15,
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": 2.81094402816e+16,
135
+ "train_batch_size": 8,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
checkpoint-194/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
+ size 5240
checkpoint-218/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-218/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22baf06235c468452afb48784bcfe17b8d6b16547f92c897a6b83b9d4be1927
3
+ size 94765560
checkpoint-218/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b107c786ae699e053540620707226aced653806a534f7bf2c3d041d5a799d0d
3
+ size 189556666
checkpoint-218/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f5981b8629d20da8d7bb452f1f8e311534ac9a1fbf9cf6ca9f99f281c14bfa
3
+ size 14308
checkpoint-218/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51016c1626b13f8e0c2274df9c63eb74ef480d103cd1eaea425e0978c8cf392
3
+ size 1064
checkpoint-218/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8475452196382429,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-218",
4
+ "epoch": 8.989690721649485,
5
+ "eval_steps": 500,
6
+ "global_step": 218,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.7157622739018088,
26
+ "eval_f1": 0.6905410405322238,
27
+ "eval_loss": 0.7444477081298828,
28
+ "eval_precision": 0.6992377248989063,
29
+ "eval_recall": 0.7157622739018088,
30
+ "eval_runtime": 1.6941,
31
+ "eval_samples_per_second": 228.443,
32
+ "eval_steps_per_second": 28.924,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7493540051679587,
38
+ "eval_f1": 0.744898505571463,
39
+ "eval_loss": 0.6171658039093018,
40
+ "eval_precision": 0.7437592422989429,
41
+ "eval_recall": 0.7493540051679587,
42
+ "eval_runtime": 1.6943,
43
+ "eval_samples_per_second": 228.408,
44
+ "eval_steps_per_second": 28.92,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7984496124031008,
50
+ "eval_f1": 0.7873621619744228,
51
+ "eval_loss": 0.5430988073348999,
52
+ "eval_precision": 0.79180344284319,
53
+ "eval_recall": 0.7984496124031008,
54
+ "eval_runtime": 1.7027,
55
+ "eval_samples_per_second": 227.289,
56
+ "eval_steps_per_second": 28.778,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.8010335917312662,
62
+ "eval_f1": 0.7974946178390901,
63
+ "eval_loss": 0.5268548130989075,
64
+ "eval_precision": 0.8005965453214461,
65
+ "eval_recall": 0.8010335917312662,
66
+ "eval_runtime": 1.6829,
67
+ "eval_samples_per_second": 229.957,
68
+ "eval_steps_per_second": 29.116,
69
+ "step": 121
70
+ },
71
+ {
72
+ "epoch": 5.979381443298969,
73
+ "eval_accuracy": 0.7493540051679587,
74
+ "eval_f1": 0.7551329793037762,
75
+ "eval_loss": 0.5810549259185791,
76
+ "eval_precision": 0.7802262423287315,
77
+ "eval_recall": 0.7493540051679587,
78
+ "eval_runtime": 1.6999,
79
+ "eval_samples_per_second": 227.658,
80
+ "eval_steps_per_second": 28.825,
81
+ "step": 145
82
+ },
83
+ {
84
+ "epoch": 6.969072164948454,
85
+ "eval_accuracy": 0.8397932816537468,
86
+ "eval_f1": 0.8354840008265724,
87
+ "eval_loss": 0.44080850481987,
88
+ "eval_precision": 0.8365717854569443,
89
+ "eval_recall": 0.8397932816537468,
90
+ "eval_runtime": 1.6785,
91
+ "eval_samples_per_second": 230.56,
92
+ "eval_steps_per_second": 29.192,
93
+ "step": 169
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8191214470284238,
98
+ "eval_f1": 0.8167837576120855,
99
+ "eval_loss": 0.46871018409729004,
100
+ "eval_precision": 0.8187643627479353,
101
+ "eval_recall": 0.8191214470284238,
102
+ "eval_runtime": 1.6719,
103
+ "eval_samples_per_second": 231.477,
104
+ "eval_steps_per_second": 29.308,
105
+ "step": 194
106
+ },
107
+ {
108
+ "epoch": 8.989690721649485,
109
+ "eval_accuracy": 0.8475452196382429,
110
+ "eval_f1": 0.8473710740005564,
111
+ "eval_loss": 0.4363822937011719,
112
+ "eval_precision": 0.8483238707679635,
113
+ "eval_recall": 0.8475452196382429,
114
+ "eval_runtime": 1.6838,
115
+ "eval_samples_per_second": 229.835,
116
+ "eval_steps_per_second": 29.101,
117
+ "step": 218
118
+ }
119
+ ],
120
+ "logging_steps": 500,
121
+ "max_steps": 360,
122
+ "num_input_tokens_seen": 0,
123
+ "num_train_epochs": 15,
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": 3.16231203168e+16,
147
+ "train_batch_size": 8,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }
checkpoint-218/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
+ size 5240
checkpoint-24/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68a1c8e7483216c3afd74e7c8f3bf326f08720513511c39fcdf37be7ae3a0552
3
  size 94765560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3bee6833ba8b12da8d51850147bb3c3b153eec346dfd3b0fda4ff730aa9026
3
  size 94765560
checkpoint-24/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea879235e07d8970f1c22eb53e2c7884154e7269b0995315fa875740c3c99644
3
  size 189556666
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856d9a47a6db002c6e55d97a99db231cee10d1fef5c0909f7d527b86c30af746
3
  size 189556666
checkpoint-24/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dfbead32b1c4ff8d1271c1899bd626bf08d46cbc21d2769431f03d7912b1368
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:202bb63ca18cd0b022bafcf6cf19faa822d2e1dbc2cdaf6b5a9bdcbe21ca7562
3
  size 14308
checkpoint-24/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3b5edb3a337b55456e10de8e5d582a8acbe41a6ddc5e0ffb6c3463e1e8bd89e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a45410ab60db58a246b1af794984e39ea7655e4cee627c4cdfe5bd40727f72a
3
  size 1064
checkpoint-24/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5193798449612403,
3
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-24",
4
  "epoch": 0.9896907216494846,
5
  "eval_steps": 500,
@@ -10,21 +10,21 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9896907216494846,
13
- "eval_accuracy": 0.5193798449612403,
14
- "eval_f1": 0.40212917110679286,
15
- "eval_loss": 1.1225358247756958,
16
- "eval_precision": 0.33630594789914475,
17
- "eval_recall": 0.5193798449612403,
18
- "eval_runtime": 1.6647,
19
- "eval_samples_per_second": 232.47,
20
- "eval_steps_per_second": 29.434,
21
  "step": 24
22
  }
23
  ],
24
  "logging_steps": 500,
25
- "max_steps": 24,
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": 3493211996160000.0,
51
  "train_batch_size": 8,
52
  "trial_name": null,
53
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6356589147286822,
3
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-24",
4
  "epoch": 0.9896907216494846,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
  "step": 24
22
  }
23
  ],
24
  "logging_steps": 500,
25
+ "max_steps": 360,
26
  "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 15,
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": 3513680035200000.0,
51
  "train_batch_size": 8,
52
  "trial_name": null,
53
  "trial_params": null
checkpoint-24/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c712b343688a0deff84bdfb1bfec65a5350ebb13af4be1817584730c46e10303
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
  size 5240
checkpoint-242/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-242/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3c3acfb39a1584bdad8c4452c6a99cc55d03b67d4754ef55bdc31be94eb5b7
3
+ size 94765560
checkpoint-242/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529f05dfd1fdfa07d440221559587dda8eded6dd4e7f89fd777f0ac7f24f5fee
3
+ size 189556666
checkpoint-242/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e731e4993f8e25825c268c79f8c5e714e7bddf10c95d3c48fd5bec091ada0032
3
+ size 14308
checkpoint-242/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781bb61f6baa40042311c990cc82713d83cdc179ccb43dbb9cdd148961a2e8ad
3
+ size 1064
checkpoint-242/trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8578811369509044,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-242",
4
+ "epoch": 9.97938144329897,
5
+ "eval_steps": 500,
6
+ "global_step": 242,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6356589147286822,
14
+ "eval_f1": 0.5920563016978556,
15
+ "eval_loss": 0.980873703956604,
16
+ "eval_precision": 0.5920482291587493,
17
+ "eval_recall": 0.6356589147286822,
18
+ "eval_runtime": 1.6668,
19
+ "eval_samples_per_second": 232.175,
20
+ "eval_steps_per_second": 29.397,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.7157622739018088,
26
+ "eval_f1": 0.6905410405322238,
27
+ "eval_loss": 0.7444477081298828,
28
+ "eval_precision": 0.6992377248989063,
29
+ "eval_recall": 0.7157622739018088,
30
+ "eval_runtime": 1.6941,
31
+ "eval_samples_per_second": 228.443,
32
+ "eval_steps_per_second": 28.924,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7493540051679587,
38
+ "eval_f1": 0.744898505571463,
39
+ "eval_loss": 0.6171658039093018,
40
+ "eval_precision": 0.7437592422989429,
41
+ "eval_recall": 0.7493540051679587,
42
+ "eval_runtime": 1.6943,
43
+ "eval_samples_per_second": 228.408,
44
+ "eval_steps_per_second": 28.92,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7984496124031008,
50
+ "eval_f1": 0.7873621619744228,
51
+ "eval_loss": 0.5430988073348999,
52
+ "eval_precision": 0.79180344284319,
53
+ "eval_recall": 0.7984496124031008,
54
+ "eval_runtime": 1.7027,
55
+ "eval_samples_per_second": 227.289,
56
+ "eval_steps_per_second": 28.778,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.8010335917312662,
62
+ "eval_f1": 0.7974946178390901,
63
+ "eval_loss": 0.5268548130989075,
64
+ "eval_precision": 0.8005965453214461,
65
+ "eval_recall": 0.8010335917312662,
66
+ "eval_runtime": 1.6829,
67
+ "eval_samples_per_second": 229.957,
68
+ "eval_steps_per_second": 29.116,
69
+ "step": 121
70
+ },
71
+ {
72
+ "epoch": 5.979381443298969,
73
+ "eval_accuracy": 0.7493540051679587,
74
+ "eval_f1": 0.7551329793037762,
75
+ "eval_loss": 0.5810549259185791,
76
+ "eval_precision": 0.7802262423287315,
77
+ "eval_recall": 0.7493540051679587,
78
+ "eval_runtime": 1.6999,
79
+ "eval_samples_per_second": 227.658,
80
+ "eval_steps_per_second": 28.825,
81
+ "step": 145
82
+ },
83
+ {
84
+ "epoch": 6.969072164948454,
85
+ "eval_accuracy": 0.8397932816537468,
86
+ "eval_f1": 0.8354840008265724,
87
+ "eval_loss": 0.44080850481987,
88
+ "eval_precision": 0.8365717854569443,
89
+ "eval_recall": 0.8397932816537468,
90
+ "eval_runtime": 1.6785,
91
+ "eval_samples_per_second": 230.56,
92
+ "eval_steps_per_second": 29.192,
93
+ "step": 169
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8191214470284238,
98
+ "eval_f1": 0.8167837576120855,
99
+ "eval_loss": 0.46871018409729004,
100
+ "eval_precision": 0.8187643627479353,
101
+ "eval_recall": 0.8191214470284238,
102
+ "eval_runtime": 1.6719,
103
+ "eval_samples_per_second": 231.477,
104
+ "eval_steps_per_second": 29.308,
105
+ "step": 194
106
+ },
107
+ {
108
+ "epoch": 8.989690721649485,
109
+ "eval_accuracy": 0.8475452196382429,
110
+ "eval_f1": 0.8473710740005564,
111
+ "eval_loss": 0.4363822937011719,
112
+ "eval_precision": 0.8483238707679635,
113
+ "eval_recall": 0.8475452196382429,
114
+ "eval_runtime": 1.6838,
115
+ "eval_samples_per_second": 229.835,
116
+ "eval_steps_per_second": 29.101,
117
+ "step": 218
118
+ },
119
+ {
120
+ "epoch": 9.97938144329897,
121
+ "eval_accuracy": 0.8578811369509044,
122
+ "eval_f1": 0.8567532661685897,
123
+ "eval_loss": 0.42906680703163147,
124
+ "eval_precision": 0.8560504853170988,
125
+ "eval_recall": 0.8578811369509044,
126
+ "eval_runtime": 1.6875,
127
+ "eval_samples_per_second": 229.333,
128
+ "eval_steps_per_second": 29.037,
129
+ "step": 242
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 360,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 15,
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": false
154
+ },
155
+ "attributes": {}
156
+ }
157
+ },
158
+ "total_flos": 3.5136800352e+16,
159
+ "train_batch_size": 8,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }
checkpoint-242/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347144964cf2be899f8dce858b11b47f463178200e095ec0ecada560c69f675a
3
+ size 5240
checkpoint-266/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-266/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40af64761e85d5fea70c649217c8cc140a31cb9ca6b3839f952a2bb9f87e0b2
3
+ size 94765560
checkpoint-266/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2157435343c02544baabe61713043b7b3749a01b1cc4aeeb2340f89faf040460
3
+ size 189556666