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
925fa09
•
1 Parent(s): 6e73b9f

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 +61 -3
  2. checkpoint-11/config.json +80 -0
  3. checkpoint-11/model.safetensors +3 -0
  4. checkpoint-11/optimizer.pt +3 -0
  5. checkpoint-11/preprocessor_config.json +9 -0
  6. checkpoint-11/rng_state.pth +3 -0
  7. checkpoint-11/scheduler.pt +3 -0
  8. checkpoint-11/trainer_state.json +54 -0
  9. checkpoint-11/training_args.bin +3 -0
  10. checkpoint-12/config.json +80 -0
  11. checkpoint-12/model.safetensors +3 -0
  12. checkpoint-12/optimizer.pt +3 -0
  13. checkpoint-12/preprocessor_config.json +9 -0
  14. checkpoint-12/rng_state.pth +3 -0
  15. checkpoint-12/scheduler.pt +3 -0
  16. checkpoint-12/trainer_state.json +54 -0
  17. checkpoint-12/training_args.bin +3 -0
  18. checkpoint-23/config.json +80 -0
  19. checkpoint-23/model.safetensors +3 -0
  20. checkpoint-23/optimizer.pt +3 -0
  21. checkpoint-23/preprocessor_config.json +9 -0
  22. checkpoint-23/rng_state.pth +3 -0
  23. checkpoint-23/scheduler.pt +3 -0
  24. checkpoint-23/trainer_state.json +66 -0
  25. checkpoint-23/training_args.bin +3 -0
  26. checkpoint-25/config.json +80 -0
  27. checkpoint-25/model.safetensors +3 -0
  28. checkpoint-25/optimizer.pt +3 -0
  29. checkpoint-25/preprocessor_config.json +9 -0
  30. checkpoint-25/rng_state.pth +3 -0
  31. checkpoint-25/scheduler.pt +3 -0
  32. checkpoint-25/trainer_state.json +66 -0
  33. checkpoint-25/training_args.bin +3 -0
  34. checkpoint-35/config.json +80 -0
  35. checkpoint-35/model.safetensors +3 -0
  36. checkpoint-35/optimizer.pt +3 -0
  37. checkpoint-35/preprocessor_config.json +9 -0
  38. checkpoint-35/rng_state.pth +3 -0
  39. checkpoint-35/scheduler.pt +3 -0
  40. checkpoint-35/trainer_state.json +78 -0
  41. checkpoint-35/training_args.bin +3 -0
  42. checkpoint-38/config.json +80 -0
  43. checkpoint-38/model.safetensors +3 -0
  44. checkpoint-38/optimizer.pt +3 -0
  45. checkpoint-38/preprocessor_config.json +9 -0
  46. checkpoint-38/rng_state.pth +3 -0
  47. checkpoint-38/scheduler.pt +3 -0
  48. checkpoint-38/trainer_state.json +78 -0
  49. checkpoint-38/training_args.bin +3 -0
  50. checkpoint-47/config.json +80 -0
README.md CHANGED
@@ -1,3 +1,61 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: ntu-spml/distilhubert
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - audiofolder
9
+ model-index:
10
+ - name: distilhubert-finetuned-cry-detector
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # distilhubert-finetuned-cry-detector
18
+
19
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 64
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.001
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
52
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
53
+ | No log | 0.9412 | 12 | 0.3494 | 0.9559 | 0.9555 | 0.9564 | 0.9559 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.44.2
59
+ - Pytorch 2.4.0+cu121
60
+ - Datasets 2.21.0
61
+ - Tokenizers 0.19.1
checkpoint-11/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-11/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587ded30bd6f5b2016dddc435305926663e21b45f69b6624b780f4463d828358
3
+ size 94763496
checkpoint-11/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ac2969c72bfbf4d666e562f2cf544a17e201d5d9ab77d34a6a987ad3b8a166
3
+ size 189552570
checkpoint-11/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-11/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed664212b7cd99a57c71d748ab059acd10207cf6e9c571c8704e3e414764217
3
+ size 14244
checkpoint-11/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6491db7666ee7abd7f00b7daf389f37f42623e77d2190d7cedb399d4309fda5
3
+ size 1064
checkpoint-11/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9411764705882353,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-11",
4
+ "epoch": 0.9361702127659575,
5
+ "eval_steps": 500,
6
+ "global_step": 11,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9361702127659575,
13
+ "eval_accuracy": 0.9411764705882353,
14
+ "eval_f1": 0.9415646417647925,
15
+ "eval_loss": 0.2156958132982254,
16
+ "eval_precision": 0.9446294240966827,
17
+ "eval_recall": 0.9411764705882353,
18
+ "eval_runtime": 3.0828,
19
+ "eval_samples_per_second": 60.66,
20
+ "eval_steps_per_second": 7.785,
21
+ "step": 11
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 55,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 5,
28
+ "save_steps": 500,
29
+ "stateful_callbacks": {
30
+ "EarlyStoppingCallback": {
31
+ "args": {
32
+ "early_stopping_patience": 3,
33
+ "early_stopping_threshold": 0.0
34
+ },
35
+ "attributes": {
36
+ "early_stopping_patience_counter": 0
37
+ }
38
+ },
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": false
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 1.1981257051356672e+16,
51
+ "train_batch_size": 8,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-11/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba58ce355cad2f4a942fe159c5c029d2f1af4a92781bdfa4ca805848d823376f
3
+ size 5240
checkpoint-12/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-12/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3667c942b60fb4aaa6da75bdc8c45dda9b2120a968bd96844eff1c2eeb6569d6
3
+ size 94763496
checkpoint-12/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaaabc411e12db72e6080d520aaf489915b57b63ecf13116359246428ab28a0d
3
+ size 189552570
checkpoint-12/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-12/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e214e6365eb6a4284a4e8e647133f419a1798d93f9dd2f8d941c02dcdc8922a
3
+ size 14244
checkpoint-12/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ac470d61d5b4613444f686474fe5bf71dbe645a07555e3c0011199a78b17ab
3
+ size 1064
checkpoint-12/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9558823529411765,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-12",
4
+ "epoch": 0.9411764705882353,
5
+ "eval_steps": 500,
6
+ "global_step": 12,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9558823529411765,
14
+ "eval_f1": 0.9555272696227192,
15
+ "eval_loss": 0.3494149148464203,
16
+ "eval_precision": 0.9564428025638596,
17
+ "eval_recall": 0.9558823529411765,
18
+ "eval_runtime": 2.8857,
19
+ "eval_samples_per_second": 70.694,
20
+ "eval_steps_per_second": 9.01,
21
+ "step": 12
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 12,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 1,
28
+ "save_steps": 500,
29
+ "stateful_callbacks": {
30
+ "EarlyStoppingCallback": {
31
+ "args": {
32
+ "early_stopping_patience": 3,
33
+ "early_stopping_threshold": 0.0
34
+ },
35
+ "attributes": {
36
+ "early_stopping_patience_counter": 0
37
+ }
38
+ },
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": true
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 1.2382512879347712e+16,
51
+ "train_batch_size": 8,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-12/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3105fda5f2c454de8afa76f767893fbe3ebf0bc8395507bd768109ec948f149d
3
+ size 5240
checkpoint-23/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-23/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcb331765a018ac29ea85db630ddaf1074010344d78be5475cd1aad2e9d9cc2
3
+ size 94763496
checkpoint-23/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869c3a62cf0034a6126c18ad904e2e7854bbb38aef9b494fa53842ef1e414046
3
+ size 189552570
checkpoint-23/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-23/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5afa942f0cac1d664ff6ebdf17eca5a923a087ce434e17a231d65b71899089
3
+ size 14244
checkpoint-23/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:747167933fffcfb0c95ca8e0a62d67e7d36cf718d4a70e795658ad992dc31698
3
+ size 1064
checkpoint-23/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9572192513368984,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-23",
4
+ "epoch": 1.9574468085106385,
5
+ "eval_steps": 500,
6
+ "global_step": 23,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9361702127659575,
13
+ "eval_accuracy": 0.9411764705882353,
14
+ "eval_f1": 0.9415646417647925,
15
+ "eval_loss": 0.2156958132982254,
16
+ "eval_precision": 0.9446294240966827,
17
+ "eval_recall": 0.9411764705882353,
18
+ "eval_runtime": 3.0828,
19
+ "eval_samples_per_second": 60.66,
20
+ "eval_steps_per_second": 7.785,
21
+ "step": 11
22
+ },
23
+ {
24
+ "epoch": 1.9574468085106385,
25
+ "eval_accuracy": 0.9572192513368984,
26
+ "eval_f1": 0.9573134708428827,
27
+ "eval_loss": 0.12373537570238113,
28
+ "eval_precision": 0.9576338229589004,
29
+ "eval_recall": 0.9572192513368984,
30
+ "eval_runtime": 2.9612,
31
+ "eval_samples_per_second": 63.15,
32
+ "eval_steps_per_second": 8.105,
33
+ "step": 23
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 55,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 5,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "EarlyStoppingCallback": {
43
+ "args": {
44
+ "early_stopping_patience": 3,
45
+ "early_stopping_threshold": 0.0
46
+ },
47
+ "attributes": {
48
+ "early_stopping_patience_counter": 0
49
+ }
50
+ },
51
+ "TrainerControl": {
52
+ "args": {
53
+ "should_epoch_stop": false,
54
+ "should_evaluate": false,
55
+ "should_log": false,
56
+ "should_save": true,
57
+ "should_training_stop": false
58
+ },
59
+ "attributes": {}
60
+ }
61
+ },
62
+ "total_flos": 2.3947368082454784e+16,
63
+ "train_batch_size": 8,
64
+ "trial_name": null,
65
+ "trial_params": null
66
+ }
checkpoint-23/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba58ce355cad2f4a942fe159c5c029d2f1af4a92781bdfa4ca805848d823376f
3
+ size 5240
checkpoint-25/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-25/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457aaf1ca73f2bd8fdf652ff897b1db85473a23401cdea192ccda04c31e902f9
3
+ size 94763496
checkpoint-25/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f78eeb88abcee76fe1f3cb427847a3366d60d465ad4933bdf631baef11c677d
3
+ size 189552570
checkpoint-25/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-25/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5c954d42fa0d2b945cf8a644f5bb95c0ecae8f78ef6f89815808920b5b330c
3
+ size 14244
checkpoint-25/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91532783b102a4c8ff5ee86df37d3662ca7a62e198729a349c132e2c9a68d5d0
3
+ size 1064
checkpoint-25/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9558823529411765,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-25",
4
+ "epoch": 1.9607843137254903,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9509803921568627,
14
+ "eval_f1": 0.9509803921568627,
15
+ "eval_loss": 0.19337645173072815,
16
+ "eval_precision": 0.9509803921568627,
17
+ "eval_recall": 0.9509803921568627,
18
+ "eval_runtime": 2.9937,
19
+ "eval_samples_per_second": 68.144,
20
+ "eval_steps_per_second": 8.685,
21
+ "step": 12
22
+ },
23
+ {
24
+ "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9558823529411765,
26
+ "eval_f1": 0.9558168094824137,
27
+ "eval_loss": 0.11207430809736252,
28
+ "eval_precision": 0.9558008500901145,
29
+ "eval_recall": 0.9558823529411765,
30
+ "eval_runtime": 2.9789,
31
+ "eval_samples_per_second": 68.481,
32
+ "eval_steps_per_second": 8.728,
33
+ "step": 25
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 48,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 4,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "EarlyStoppingCallback": {
43
+ "args": {
44
+ "early_stopping_patience": 3,
45
+ "early_stopping_threshold": 0.0
46
+ },
47
+ "attributes": {
48
+ "early_stopping_patience_counter": 0
49
+ }
50
+ },
51
+ "TrainerControl": {
52
+ "args": {
53
+ "should_epoch_stop": false,
54
+ "should_evaluate": false,
55
+ "should_log": false,
56
+ "should_save": true,
57
+ "should_training_stop": false
58
+ },
59
+ "attributes": {}
60
+ }
61
+ },
62
+ "total_flos": 2.632285534507315e+16,
63
+ "train_batch_size": 8,
64
+ "trial_name": null,
65
+ "trial_params": null
66
+ }
checkpoint-25/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08c1ef2199623b781e926f1d827964186fca47326620731302bfe37c5d058b9
3
+ size 5240
checkpoint-35/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-35/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ac590ecbfe521110ab81f16af790aa2a6f1cb4ab70317973e13165d0709582
3
+ size 94763496
checkpoint-35/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5616c1cbc4a632a4500d7065ca4131e413c67941e4f867d528e017d8f4114178
3
+ size 189552570
checkpoint-35/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-35/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40c7263da12c8166f64ce9b0988018ca7ba311284f65e80ebcaa3856ca7de3f
3
+ size 14244
checkpoint-35/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928490201c93ddf3bddd80ff74fac96f745a82dfb6404304be920725c0a03457
3
+ size 1064
checkpoint-35/trainer_state.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9572192513368984,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-23",
4
+ "epoch": 2.978723404255319,
5
+ "eval_steps": 500,
6
+ "global_step": 35,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9361702127659575,
13
+ "eval_accuracy": 0.9411764705882353,
14
+ "eval_f1": 0.9415646417647925,
15
+ "eval_loss": 0.2156958132982254,
16
+ "eval_precision": 0.9446294240966827,
17
+ "eval_recall": 0.9411764705882353,
18
+ "eval_runtime": 3.0828,
19
+ "eval_samples_per_second": 60.66,
20
+ "eval_steps_per_second": 7.785,
21
+ "step": 11
22
+ },
23
+ {
24
+ "epoch": 1.9574468085106385,
25
+ "eval_accuracy": 0.9572192513368984,
26
+ "eval_f1": 0.9573134708428827,
27
+ "eval_loss": 0.12373537570238113,
28
+ "eval_precision": 0.9576338229589004,
29
+ "eval_recall": 0.9572192513368984,
30
+ "eval_runtime": 2.9612,
31
+ "eval_samples_per_second": 63.15,
32
+ "eval_steps_per_second": 8.105,
33
+ "step": 23
34
+ },
35
+ {
36
+ "epoch": 2.978723404255319,
37
+ "eval_accuracy": 0.9518716577540107,
38
+ "eval_f1": 0.9521892523530119,
39
+ "eval_loss": 0.1370447278022766,
40
+ "eval_precision": 0.9552156165178733,
41
+ "eval_recall": 0.9518716577540107,
42
+ "eval_runtime": 2.9378,
43
+ "eval_samples_per_second": 63.653,
44
+ "eval_steps_per_second": 8.169,
45
+ "step": 35
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 55,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "EarlyStoppingCallback": {
55
+ "args": {
56
+ "early_stopping_patience": 3,
57
+ "early_stopping_threshold": 0.0
58
+ },
59
+ "attributes": {
60
+ "early_stopping_patience_counter": 0
61
+ }
62
+ },
63
+ "TrainerControl": {
64
+ "args": {
65
+ "should_epoch_stop": false,
66
+ "should_evaluate": false,
67
+ "should_log": false,
68
+ "should_save": true,
69
+ "should_training_stop": false
70
+ },
71
+ "attributes": {}
72
+ }
73
+ },
74
+ "total_flos": 3.5925100159126656e+16,
75
+ "train_batch_size": 8,
76
+ "trial_name": null,
77
+ "trial_params": null
78
+ }
checkpoint-35/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba58ce355cad2f4a942fe159c5c029d2f1af4a92781bdfa4ca805848d823376f
3
+ size 5240
checkpoint-38/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-38/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365a9fb794f55008ff39b21086b11700c109a194efb2127a6db2145604a614b6
3
+ size 94763496
checkpoint-38/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198372300c7cb71ea5cd197e4b8f17970da74cfc971f4a284751e8c5c2fe5397
3
+ size 189552570
checkpoint-38/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-38/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780c51c50482e6e8f628b4687957abc3bb4ff7f96b977c02d8538cf6f0d2d494
3
+ size 14244
checkpoint-38/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ddec5715a7e2a3cc7175b7f159a7e1fd2303094015b4bffdae6a236e889974
3
+ size 1064
checkpoint-38/trainer_state.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9607843137254902,
3
+ "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-38",
4
+ "epoch": 2.980392156862745,
5
+ "eval_steps": 500,
6
+ "global_step": 38,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9411764705882353,
13
+ "eval_accuracy": 0.9509803921568627,
14
+ "eval_f1": 0.9509803921568627,
15
+ "eval_loss": 0.19337645173072815,
16
+ "eval_precision": 0.9509803921568627,
17
+ "eval_recall": 0.9509803921568627,
18
+ "eval_runtime": 2.9937,
19
+ "eval_samples_per_second": 68.144,
20
+ "eval_steps_per_second": 8.685,
21
+ "step": 12
22
+ },
23
+ {
24
+ "epoch": 1.9607843137254903,
25
+ "eval_accuracy": 0.9558823529411765,
26
+ "eval_f1": 0.9558168094824137,
27
+ "eval_loss": 0.11207430809736252,
28
+ "eval_precision": 0.9558008500901145,
29
+ "eval_recall": 0.9558823529411765,
30
+ "eval_runtime": 2.9789,
31
+ "eval_samples_per_second": 68.481,
32
+ "eval_steps_per_second": 8.728,
33
+ "step": 25
34
+ },
35
+ {
36
+ "epoch": 2.980392156862745,
37
+ "eval_accuracy": 0.9607843137254902,
38
+ "eval_f1": 0.9608937528499771,
39
+ "eval_loss": 0.08983828127384186,
40
+ "eval_precision": 0.9611995291537668,
41
+ "eval_recall": 0.9607843137254902,
42
+ "eval_runtime": 2.927,
43
+ "eval_samples_per_second": 69.695,
44
+ "eval_steps_per_second": 8.883,
45
+ "step": 38
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 48,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "EarlyStoppingCallback": {
55
+ "args": {
56
+ "early_stopping_patience": 3,
57
+ "early_stopping_threshold": 0.0
58
+ },
59
+ "attributes": {
60
+ "early_stopping_patience_counter": 0
61
+ }
62
+ },
63
+ "TrainerControl": {
64
+ "args": {
65
+ "should_epoch_stop": false,
66
+ "should_evaluate": false,
67
+ "should_log": false,
68
+ "should_save": true,
69
+ "should_training_stop": false
70
+ },
71
+ "attributes": {}
72
+ }
73
+ },
74
+ "total_flos": 3.947040143988326e+16,
75
+ "train_batch_size": 8,
76
+ "trial_name": null,
77
+ "trial_params": null
78
+ }
checkpoint-38/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08c1ef2199623b781e926f1d827964186fca47326620731302bfe37c5d058b9
3
+ size 5240
checkpoint-47/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
+ }