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
969bb37
·
verified ·
1 Parent(s): e0f3ecc

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 +105 -3
  2. checkpoint-111/config.json +84 -0
  3. checkpoint-111/model.safetensors +3 -0
  4. checkpoint-111/optimizer.pt +3 -0
  5. checkpoint-111/preprocessor_config.json +9 -0
  6. checkpoint-111/rng_state.pth +3 -0
  7. checkpoint-111/scheduler.pt +3 -0
  8. checkpoint-111/trainer_state.json +114 -0
  9. checkpoint-111/training_args.bin +3 -0
  10. checkpoint-130/config.json +84 -0
  11. checkpoint-130/model.safetensors +3 -0
  12. checkpoint-130/optimizer.pt +3 -0
  13. checkpoint-130/preprocessor_config.json +9 -0
  14. checkpoint-130/rng_state.pth +3 -0
  15. checkpoint-130/scheduler.pt +3 -0
  16. checkpoint-130/trainer_state.json +126 -0
  17. checkpoint-130/training_args.bin +3 -0
  18. checkpoint-135/config.json +84 -0
  19. checkpoint-135/model.safetensors +3 -0
  20. checkpoint-135/optimizer.pt +3 -0
  21. checkpoint-135/preprocessor_config.json +9 -0
  22. checkpoint-135/rng_state.pth +3 -0
  23. checkpoint-135/scheduler.pt +3 -0
  24. checkpoint-135/trainer_state.json +60 -0
  25. checkpoint-135/training_args.bin +3 -0
  26. checkpoint-136/config.json +84 -0
  27. checkpoint-136/model.safetensors +3 -0
  28. checkpoint-136/optimizer.pt +3 -0
  29. checkpoint-136/preprocessor_config.json +9 -0
  30. checkpoint-136/rng_state.pth +3 -0
  31. checkpoint-136/scheduler.pt +3 -0
  32. checkpoint-136/trainer_state.json +60 -0
  33. checkpoint-136/training_args.bin +3 -0
  34. checkpoint-149/config.json +84 -0
  35. checkpoint-149/model.safetensors +3 -0
  36. checkpoint-149/optimizer.pt +3 -0
  37. checkpoint-149/preprocessor_config.json +9 -0
  38. checkpoint-149/rng_state.pth +3 -0
  39. checkpoint-149/scheduler.pt +3 -0
  40. checkpoint-149/trainer_state.json +138 -0
  41. checkpoint-149/training_args.bin +3 -0
  42. checkpoint-167/config.json +84 -0
  43. checkpoint-167/model.safetensors +3 -0
  44. checkpoint-167/optimizer.pt +3 -0
  45. checkpoint-167/preprocessor_config.json +9 -0
  46. checkpoint-167/rng_state.pth +3 -0
  47. checkpoint-167/scheduler.pt +3 -0
  48. checkpoint-167/trainer_state.json +150 -0
  49. checkpoint-167/training_args.bin +3 -0
  50. checkpoint-18/config.json +84 -0
README.md CHANGED
@@ -1,3 +1,105 @@
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
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ - precision
13
+ - recall
14
+ model-index:
15
+ - name: distilhubert-finetuned-mixed-data
16
+ results:
17
+ - task:
18
+ name: Audio Classification
19
+ type: audio-classification
20
+ dataset:
21
+ name: audiofolder
22
+ type: audiofolder
23
+ config: default
24
+ split: train
25
+ args: default
26
+ metrics:
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value: 0.9026845637583892
30
+ - name: F1
31
+ type: f1
32
+ value: 0.9017814679012008
33
+ - name: Precision
34
+ type: precision
35
+ value: 0.901095676384633
36
+ - name: Recall
37
+ type: recall
38
+ value: 0.9026845637583892
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # distilhubert-finetuned-mixed-data
45
+
46
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.2976
49
+ - Accuracy: 0.9027
50
+ - F1: 0.9018
51
+ - Precision: 0.9011
52
+ - Recall: 0.9027
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 0.0001
72
+ - train_batch_size: 8
73
+ - eval_batch_size: 8
74
+ - seed: 123
75
+ - gradient_accumulation_steps: 8
76
+ - total_train_batch_size: 64
77
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
78
+ - lr_scheduler_type: cosine
79
+ - lr_scheduler_warmup_ratio: 0.001
80
+ - num_epochs: 12
81
+
82
+ ### Training results
83
+
84
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
+ | No log | 0.9664 | 18 | 0.6696 | 0.7819 | 0.7264 | 0.6898 | 0.7819 |
87
+ | No log | 1.9866 | 37 | 0.5068 | 0.7752 | 0.7203 | 0.6849 | 0.7752 |
88
+ | No log | 2.9530 | 55 | 0.4304 | 0.8087 | 0.7535 | 0.7242 | 0.8087 |
89
+ | No log | 3.9732 | 74 | 0.4109 | 0.8523 | 0.8434 | 0.8728 | 0.8523 |
90
+ | No log | 4.9933 | 93 | 0.3263 | 0.8725 | 0.8718 | 0.8719 | 0.8725 |
91
+ | No log | 5.9597 | 111 | 0.3036 | 0.8826 | 0.8824 | 0.8824 | 0.8826 |
92
+ | No log | 6.9799 | 130 | 0.3046 | 0.8893 | 0.8876 | 0.8892 | 0.8893 |
93
+ | No log | 8.0 | 149 | 0.3244 | 0.8758 | 0.8770 | 0.8787 | 0.8758 |
94
+ | No log | 8.9664 | 167 | 0.2962 | 0.9027 | 0.9018 | 0.9012 | 0.9027 |
95
+ | No log | 9.9866 | 186 | 0.2971 | 0.9027 | 0.9010 | 0.9014 | 0.9027 |
96
+ | No log | 10.9530 | 204 | 0.2974 | 0.9094 | 0.9082 | 0.9077 | 0.9094 |
97
+ | No log | 11.5973 | 216 | 0.2976 | 0.9027 | 0.9018 | 0.9011 | 0.9027 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.44.2
103
+ - Pytorch 2.4.0+cu121
104
+ - Datasets 2.21.0
105
+ - Tokenizers 0.19.1
checkpoint-111/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_asphyxia",
53
+ "1": "1s_hunger",
54
+ "2": "1s_normal",
55
+ "3": "1s_pain"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "0",
61
+ "1s_hunger": "1",
62
+ "1s_normal": "2",
63
+ "1s_pain": "3"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }
checkpoint-111/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8afb68ff2611e3603dee528e572e6fc36c40e47cec34c6ee683636922c8055e1
3
+ size 94765560
checkpoint-111/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:105e2897a04f3a74cea8691093cd964cb3e2476cb37888e94bd97ac020d7bc23
3
+ size 189556666
checkpoint-111/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-111/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f43e7fdf5def6846b069020fb2803b19ffc2aab112709cf440ff32a8a2bc9b
3
+ size 14308
checkpoint-111/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5bf82e806804b25d214305b99f2c178bc6f19a61f077621eaca5b3cb5523cd
3
+ size 1064
checkpoint-111/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8825503355704698,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-111",
4
+ "epoch": 5.959731543624161,
5
+ "eval_steps": 500,
6
+ "global_step": 111,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9664429530201343,
13
+ "eval_accuracy": 0.7818791946308725,
14
+ "eval_f1": 0.7264205130236912,
15
+ "eval_loss": 0.669560968875885,
16
+ "eval_precision": 0.689807639599501,
17
+ "eval_recall": 0.7818791946308725,
18
+ "eval_runtime": 0.9033,
19
+ "eval_samples_per_second": 329.896,
20
+ "eval_steps_per_second": 42.067,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 1.9865771812080537,
25
+ "eval_accuracy": 0.7751677852348994,
26
+ "eval_f1": 0.7202681570933687,
27
+ "eval_loss": 0.5067932605743408,
28
+ "eval_precision": 0.684911313518696,
29
+ "eval_recall": 0.7751677852348994,
30
+ "eval_runtime": 0.907,
31
+ "eval_samples_per_second": 328.546,
32
+ "eval_steps_per_second": 41.895,
33
+ "step": 37
34
+ },
35
+ {
36
+ "epoch": 2.953020134228188,
37
+ "eval_accuracy": 0.8087248322147651,
38
+ "eval_f1": 0.7535236037076262,
39
+ "eval_loss": 0.43038079142570496,
40
+ "eval_precision": 0.7241626365959,
41
+ "eval_recall": 0.8087248322147651,
42
+ "eval_runtime": 0.8664,
43
+ "eval_samples_per_second": 343.963,
44
+ "eval_steps_per_second": 43.861,
45
+ "step": 55
46
+ },
47
+ {
48
+ "epoch": 3.9731543624161074,
49
+ "eval_accuracy": 0.8523489932885906,
50
+ "eval_f1": 0.8433916249277822,
51
+ "eval_loss": 0.4109182059764862,
52
+ "eval_precision": 0.8727817866814688,
53
+ "eval_recall": 0.8523489932885906,
54
+ "eval_runtime": 0.8712,
55
+ "eval_samples_per_second": 342.059,
56
+ "eval_steps_per_second": 43.618,
57
+ "step": 74
58
+ },
59
+ {
60
+ "epoch": 4.993288590604027,
61
+ "eval_accuracy": 0.87248322147651,
62
+ "eval_f1": 0.8717711524765707,
63
+ "eval_loss": 0.3263051509857178,
64
+ "eval_precision": 0.8718521382399975,
65
+ "eval_recall": 0.87248322147651,
66
+ "eval_runtime": 0.87,
67
+ "eval_samples_per_second": 342.548,
68
+ "eval_steps_per_second": 43.681,
69
+ "step": 93
70
+ },
71
+ {
72
+ "epoch": 5.959731543624161,
73
+ "eval_accuracy": 0.8825503355704698,
74
+ "eval_f1": 0.8824400125399595,
75
+ "eval_loss": 0.3035907447338104,
76
+ "eval_precision": 0.8824270850226767,
77
+ "eval_recall": 0.8825503355704698,
78
+ "eval_runtime": 0.8921,
79
+ "eval_samples_per_second": 334.055,
80
+ "eval_steps_per_second": 42.598,
81
+ "step": 111
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 216,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 12,
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": 1.62379776384e+16,
111
+ "train_batch_size": 8,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-111/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296be9afae72ab3934d873f0cf92f87ef76899c18b11651de670afb49aa1a5d6
3
+ size 5240
checkpoint-130/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_asphyxia",
53
+ "1": "1s_hunger",
54
+ "2": "1s_normal",
55
+ "3": "1s_pain"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "0",
61
+ "1s_hunger": "1",
62
+ "1s_normal": "2",
63
+ "1s_pain": "3"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }
checkpoint-130/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3274a950ef7996900990e6a908894c38407a87245d2e54fd2d49a70f893d18d7
3
+ size 94765560
checkpoint-130/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350d7e738f5a2fe60a4aaaa7bf1f954bab46678f8d6d6a8b53d70e92d336058a
3
+ size 189556666
checkpoint-130/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-130/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ce1903887f6eefecdbafa965766c8b4e5f6264b39c386f85053529854ad6aa
3
+ size 14308
checkpoint-130/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c8f63f56197268202aa5b134a342d5425bd11184ac819d7eb62d725e5d31de3
3
+ size 1064
checkpoint-130/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.889261744966443,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-130",
4
+ "epoch": 6.97986577181208,
5
+ "eval_steps": 500,
6
+ "global_step": 130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9664429530201343,
13
+ "eval_accuracy": 0.7818791946308725,
14
+ "eval_f1": 0.7264205130236912,
15
+ "eval_loss": 0.669560968875885,
16
+ "eval_precision": 0.689807639599501,
17
+ "eval_recall": 0.7818791946308725,
18
+ "eval_runtime": 0.9033,
19
+ "eval_samples_per_second": 329.896,
20
+ "eval_steps_per_second": 42.067,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 1.9865771812080537,
25
+ "eval_accuracy": 0.7751677852348994,
26
+ "eval_f1": 0.7202681570933687,
27
+ "eval_loss": 0.5067932605743408,
28
+ "eval_precision": 0.684911313518696,
29
+ "eval_recall": 0.7751677852348994,
30
+ "eval_runtime": 0.907,
31
+ "eval_samples_per_second": 328.546,
32
+ "eval_steps_per_second": 41.895,
33
+ "step": 37
34
+ },
35
+ {
36
+ "epoch": 2.953020134228188,
37
+ "eval_accuracy": 0.8087248322147651,
38
+ "eval_f1": 0.7535236037076262,
39
+ "eval_loss": 0.43038079142570496,
40
+ "eval_precision": 0.7241626365959,
41
+ "eval_recall": 0.8087248322147651,
42
+ "eval_runtime": 0.8664,
43
+ "eval_samples_per_second": 343.963,
44
+ "eval_steps_per_second": 43.861,
45
+ "step": 55
46
+ },
47
+ {
48
+ "epoch": 3.9731543624161074,
49
+ "eval_accuracy": 0.8523489932885906,
50
+ "eval_f1": 0.8433916249277822,
51
+ "eval_loss": 0.4109182059764862,
52
+ "eval_precision": 0.8727817866814688,
53
+ "eval_recall": 0.8523489932885906,
54
+ "eval_runtime": 0.8712,
55
+ "eval_samples_per_second": 342.059,
56
+ "eval_steps_per_second": 43.618,
57
+ "step": 74
58
+ },
59
+ {
60
+ "epoch": 4.993288590604027,
61
+ "eval_accuracy": 0.87248322147651,
62
+ "eval_f1": 0.8717711524765707,
63
+ "eval_loss": 0.3263051509857178,
64
+ "eval_precision": 0.8718521382399975,
65
+ "eval_recall": 0.87248322147651,
66
+ "eval_runtime": 0.87,
67
+ "eval_samples_per_second": 342.548,
68
+ "eval_steps_per_second": 43.681,
69
+ "step": 93
70
+ },
71
+ {
72
+ "epoch": 5.959731543624161,
73
+ "eval_accuracy": 0.8825503355704698,
74
+ "eval_f1": 0.8824400125399595,
75
+ "eval_loss": 0.3035907447338104,
76
+ "eval_precision": 0.8824270850226767,
77
+ "eval_recall": 0.8825503355704698,
78
+ "eval_runtime": 0.8921,
79
+ "eval_samples_per_second": 334.055,
80
+ "eval_steps_per_second": 42.598,
81
+ "step": 111
82
+ },
83
+ {
84
+ "epoch": 6.97986577181208,
85
+ "eval_accuracy": 0.889261744966443,
86
+ "eval_f1": 0.8876321254746313,
87
+ "eval_loss": 0.3046204149723053,
88
+ "eval_precision": 0.8891935449502327,
89
+ "eval_recall": 0.889261744966443,
90
+ "eval_runtime": 0.894,
91
+ "eval_samples_per_second": 333.317,
92
+ "eval_steps_per_second": 42.504,
93
+ "step": 130
94
+ }
95
+ ],
96
+ "logging_steps": 500,
97
+ "max_steps": 216,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 12,
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": 1.89443072448e+16,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
checkpoint-130/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296be9afae72ab3934d873f0cf92f87ef76899c18b11651de670afb49aa1a5d6
3
+ size 5240
checkpoint-135/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_pain",
53
+ "1": "1s_normal",
54
+ "2": "1s_asphyxia",
55
+ "3": "1s_hunger"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "2",
61
+ "1s_hunger": "3",
62
+ "1s_normal": "1",
63
+ "1s_pain": "0"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }
checkpoint-135/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b04e455cb28d03199ae0547ed3d379f784d8b87502f896e8601b3a6dbbf5ed5
3
+ size 94765560
checkpoint-135/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0a3920a3219c17d5246c0b0cc4d972ce476ded5ff479d1851bfa1e197f3c7d
3
+ size 189556666
checkpoint-135/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-135/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76852e73dfcd3d0470d5a6ce48f93321160ffa41866b87f241dcdf4dc19c2da
3
+ size 14244
checkpoint-135/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a799a5fee1cd04ce0f342f7f115c3a396839d512d5eace9370b47e189b3242
3
+ size 1064
checkpoint-135/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8301435406698564,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-135",
4
+ "epoch": 2.958904109589041,
5
+ "eval_steps": 500,
6
+ "global_step": 135,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9863013698630136,
13
+ "eval_accuracy": 0.777511961722488,
14
+ "eval_loss": 0.561026930809021,
15
+ "eval_runtime": 1.0204,
16
+ "eval_samples_per_second": 409.634,
17
+ "eval_steps_per_second": 51.939,
18
+ "step": 45
19
+ },
20
+ {
21
+ "epoch": 1.9945205479452055,
22
+ "eval_accuracy": 0.8133971291866029,
23
+ "eval_loss": 0.43190622329711914,
24
+ "eval_runtime": 1.0273,
25
+ "eval_samples_per_second": 406.884,
26
+ "eval_steps_per_second": 51.591,
27
+ "step": 91
28
+ },
29
+ {
30
+ "epoch": 2.958904109589041,
31
+ "eval_accuracy": 0.8301435406698564,
32
+ "eval_loss": 0.40697425603866577,
33
+ "eval_runtime": 1.063,
34
+ "eval_samples_per_second": 393.225,
35
+ "eval_steps_per_second": 49.859,
36
+ "step": 135
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 135,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "stateful_callbacks": {
45
+ "TrainerControl": {
46
+ "args": {
47
+ "should_epoch_stop": false,
48
+ "should_evaluate": false,
49
+ "should_log": false,
50
+ "should_save": true,
51
+ "should_training_stop": true
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 1.964476902528e+16,
57
+ "train_batch_size": 8,
58
+ "trial_name": null,
59
+ "trial_params": null
60
+ }
checkpoint-135/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58bee4dcd5fe0b58b30175a3b929b42d49bdcef85fb7a1c05e452879211375f4
3
+ size 5240
checkpoint-136/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_hunger",
53
+ "1": "1s_pain",
54
+ "2": "1s_normal",
55
+ "3": "1s_asphyxia"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "3",
61
+ "1s_hunger": "0",
62
+ "1s_normal": "2",
63
+ "1s_pain": "1"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }
checkpoint-136/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b4450db25ba5f0d510ec4e3306e7f346b1218297cc27efb9eb5549200298f0
3
+ size 94765560
checkpoint-136/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4a094ba38c61e01742a1399183042512757ac7cef90decc84fa9ddd3e292d0
3
+ size 189556666
checkpoint-136/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-136/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c109a88cfed134d7433f6a487d90e7431aae064934a30eee009d35114d91a8
3
+ size 14244
checkpoint-136/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02db814972e9031670f30187fddad96ad1438ee30746ac0e08e7fe64a2319de1
3
+ size 1064
checkpoint-136/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8397129186602871,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-136",
4
+ "epoch": 2.9808219178082194,
5
+ "eval_steps": 500,
6
+ "global_step": 136,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9863013698630136,
13
+ "eval_accuracy": 0.7942583732057417,
14
+ "eval_loss": 0.5718334913253784,
15
+ "eval_runtime": 1.0678,
16
+ "eval_samples_per_second": 391.448,
17
+ "eval_steps_per_second": 49.633,
18
+ "step": 45
19
+ },
20
+ {
21
+ "epoch": 1.9945205479452055,
22
+ "eval_accuracy": 0.80622009569378,
23
+ "eval_loss": 0.45444098114967346,
24
+ "eval_runtime": 1.0491,
25
+ "eval_samples_per_second": 398.444,
26
+ "eval_steps_per_second": 50.52,
27
+ "step": 91
28
+ },
29
+ {
30
+ "epoch": 2.9808219178082194,
31
+ "eval_accuracy": 0.8397129186602871,
32
+ "eval_loss": 0.3911355435848236,
33
+ "eval_runtime": 1.0412,
34
+ "eval_samples_per_second": 401.464,
35
+ "eval_steps_per_second": 50.903,
36
+ "step": 136
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 270,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 6,
43
+ "save_steps": 500,
44
+ "stateful_callbacks": {
45
+ "TrainerControl": {
46
+ "args": {
47
+ "should_epoch_stop": false,
48
+ "should_evaluate": false,
49
+ "should_log": false,
50
+ "should_save": true,
51
+ "should_training_stop": false
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 1.991540198592e+16,
57
+ "train_batch_size": 8,
58
+ "trial_name": null,
59
+ "trial_params": null
60
+ }
checkpoint-136/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9d41ebe9cd4a0039236a5c6d5456e94aa46eef860ab4ccc1c1578a2a2cbc20
3
+ size 5240
checkpoint-149/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_asphyxia",
53
+ "1": "1s_hunger",
54
+ "2": "1s_normal",
55
+ "3": "1s_pain"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "0",
61
+ "1s_hunger": "1",
62
+ "1s_normal": "2",
63
+ "1s_pain": "3"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }
checkpoint-149/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39cbcf4e451fec6c5adf024114939d0eaeecc9eae9b358985fe76e17a289c71
3
+ size 94765560
checkpoint-149/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973fe719a94fc7d292682b0cea4b719eda84c95a7325e50f50602418d8e621c8
3
+ size 189556666
checkpoint-149/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-149/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab240972588ded48883e00b3a1029ab3ff4045470da6447d45f5de8bcf4eb20
3
+ size 14308
checkpoint-149/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9ad5796e032f21e10d21d1114e9452b0cd107cc5a4f541c7c91883714189d2
3
+ size 1064
checkpoint-149/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.889261744966443,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-130",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 149,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9664429530201343,
13
+ "eval_accuracy": 0.7818791946308725,
14
+ "eval_f1": 0.7264205130236912,
15
+ "eval_loss": 0.669560968875885,
16
+ "eval_precision": 0.689807639599501,
17
+ "eval_recall": 0.7818791946308725,
18
+ "eval_runtime": 0.9033,
19
+ "eval_samples_per_second": 329.896,
20
+ "eval_steps_per_second": 42.067,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 1.9865771812080537,
25
+ "eval_accuracy": 0.7751677852348994,
26
+ "eval_f1": 0.7202681570933687,
27
+ "eval_loss": 0.5067932605743408,
28
+ "eval_precision": 0.684911313518696,
29
+ "eval_recall": 0.7751677852348994,
30
+ "eval_runtime": 0.907,
31
+ "eval_samples_per_second": 328.546,
32
+ "eval_steps_per_second": 41.895,
33
+ "step": 37
34
+ },
35
+ {
36
+ "epoch": 2.953020134228188,
37
+ "eval_accuracy": 0.8087248322147651,
38
+ "eval_f1": 0.7535236037076262,
39
+ "eval_loss": 0.43038079142570496,
40
+ "eval_precision": 0.7241626365959,
41
+ "eval_recall": 0.8087248322147651,
42
+ "eval_runtime": 0.8664,
43
+ "eval_samples_per_second": 343.963,
44
+ "eval_steps_per_second": 43.861,
45
+ "step": 55
46
+ },
47
+ {
48
+ "epoch": 3.9731543624161074,
49
+ "eval_accuracy": 0.8523489932885906,
50
+ "eval_f1": 0.8433916249277822,
51
+ "eval_loss": 0.4109182059764862,
52
+ "eval_precision": 0.8727817866814688,
53
+ "eval_recall": 0.8523489932885906,
54
+ "eval_runtime": 0.8712,
55
+ "eval_samples_per_second": 342.059,
56
+ "eval_steps_per_second": 43.618,
57
+ "step": 74
58
+ },
59
+ {
60
+ "epoch": 4.993288590604027,
61
+ "eval_accuracy": 0.87248322147651,
62
+ "eval_f1": 0.8717711524765707,
63
+ "eval_loss": 0.3263051509857178,
64
+ "eval_precision": 0.8718521382399975,
65
+ "eval_recall": 0.87248322147651,
66
+ "eval_runtime": 0.87,
67
+ "eval_samples_per_second": 342.548,
68
+ "eval_steps_per_second": 43.681,
69
+ "step": 93
70
+ },
71
+ {
72
+ "epoch": 5.959731543624161,
73
+ "eval_accuracy": 0.8825503355704698,
74
+ "eval_f1": 0.8824400125399595,
75
+ "eval_loss": 0.3035907447338104,
76
+ "eval_precision": 0.8824270850226767,
77
+ "eval_recall": 0.8825503355704698,
78
+ "eval_runtime": 0.8921,
79
+ "eval_samples_per_second": 334.055,
80
+ "eval_steps_per_second": 42.598,
81
+ "step": 111
82
+ },
83
+ {
84
+ "epoch": 6.97986577181208,
85
+ "eval_accuracy": 0.889261744966443,
86
+ "eval_f1": 0.8876321254746313,
87
+ "eval_loss": 0.3046204149723053,
88
+ "eval_precision": 0.8891935449502327,
89
+ "eval_recall": 0.889261744966443,
90
+ "eval_runtime": 0.894,
91
+ "eval_samples_per_second": 333.317,
92
+ "eval_steps_per_second": 42.504,
93
+ "step": 130
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8758389261744967,
98
+ "eval_f1": 0.8770158544888631,
99
+ "eval_loss": 0.32443463802337646,
100
+ "eval_precision": 0.8787167286554325,
101
+ "eval_recall": 0.8758389261744967,
102
+ "eval_runtime": 0.9094,
103
+ "eval_samples_per_second": 327.69,
104
+ "eval_steps_per_second": 41.786,
105
+ "step": 149
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 216,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 12,
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": 2.16506368512e+16,
135
+ "train_batch_size": 8,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
checkpoint-149/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296be9afae72ab3934d873f0cf92f87ef76899c18b11651de670afb49aa1a5d6
3
+ size 5240
checkpoint-167/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_asphyxia",
53
+ "1": "1s_hunger",
54
+ "2": "1s_normal",
55
+ "3": "1s_pain"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "0",
61
+ "1s_hunger": "1",
62
+ "1s_normal": "2",
63
+ "1s_pain": "3"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }
checkpoint-167/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99cb84823dab9c2514de746659bd19475207dd5160180a21c19e06c9ee8923f4
3
+ size 94765560
checkpoint-167/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a4ee5fa0c7807441f156f570af2346069baaf0c030dadec1c4ab4098330d91
3
+ size 189556666
checkpoint-167/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-167/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65b53d3587b97669b32f24817b54a83a0d7880d65d1fed7315353b45d1d4bc5
3
+ size 14308
checkpoint-167/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eceb16cd0387067793218afd9bb8832dfde9b5f16ebc34cc0e5baf4d23ab80ef
3
+ size 1064
checkpoint-167/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9026845637583892,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-167",
4
+ "epoch": 8.966442953020135,
5
+ "eval_steps": 500,
6
+ "global_step": 167,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9664429530201343,
13
+ "eval_accuracy": 0.7818791946308725,
14
+ "eval_f1": 0.7264205130236912,
15
+ "eval_loss": 0.669560968875885,
16
+ "eval_precision": 0.689807639599501,
17
+ "eval_recall": 0.7818791946308725,
18
+ "eval_runtime": 0.9033,
19
+ "eval_samples_per_second": 329.896,
20
+ "eval_steps_per_second": 42.067,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 1.9865771812080537,
25
+ "eval_accuracy": 0.7751677852348994,
26
+ "eval_f1": 0.7202681570933687,
27
+ "eval_loss": 0.5067932605743408,
28
+ "eval_precision": 0.684911313518696,
29
+ "eval_recall": 0.7751677852348994,
30
+ "eval_runtime": 0.907,
31
+ "eval_samples_per_second": 328.546,
32
+ "eval_steps_per_second": 41.895,
33
+ "step": 37
34
+ },
35
+ {
36
+ "epoch": 2.953020134228188,
37
+ "eval_accuracy": 0.8087248322147651,
38
+ "eval_f1": 0.7535236037076262,
39
+ "eval_loss": 0.43038079142570496,
40
+ "eval_precision": 0.7241626365959,
41
+ "eval_recall": 0.8087248322147651,
42
+ "eval_runtime": 0.8664,
43
+ "eval_samples_per_second": 343.963,
44
+ "eval_steps_per_second": 43.861,
45
+ "step": 55
46
+ },
47
+ {
48
+ "epoch": 3.9731543624161074,
49
+ "eval_accuracy": 0.8523489932885906,
50
+ "eval_f1": 0.8433916249277822,
51
+ "eval_loss": 0.4109182059764862,
52
+ "eval_precision": 0.8727817866814688,
53
+ "eval_recall": 0.8523489932885906,
54
+ "eval_runtime": 0.8712,
55
+ "eval_samples_per_second": 342.059,
56
+ "eval_steps_per_second": 43.618,
57
+ "step": 74
58
+ },
59
+ {
60
+ "epoch": 4.993288590604027,
61
+ "eval_accuracy": 0.87248322147651,
62
+ "eval_f1": 0.8717711524765707,
63
+ "eval_loss": 0.3263051509857178,
64
+ "eval_precision": 0.8718521382399975,
65
+ "eval_recall": 0.87248322147651,
66
+ "eval_runtime": 0.87,
67
+ "eval_samples_per_second": 342.548,
68
+ "eval_steps_per_second": 43.681,
69
+ "step": 93
70
+ },
71
+ {
72
+ "epoch": 5.959731543624161,
73
+ "eval_accuracy": 0.8825503355704698,
74
+ "eval_f1": 0.8824400125399595,
75
+ "eval_loss": 0.3035907447338104,
76
+ "eval_precision": 0.8824270850226767,
77
+ "eval_recall": 0.8825503355704698,
78
+ "eval_runtime": 0.8921,
79
+ "eval_samples_per_second": 334.055,
80
+ "eval_steps_per_second": 42.598,
81
+ "step": 111
82
+ },
83
+ {
84
+ "epoch": 6.97986577181208,
85
+ "eval_accuracy": 0.889261744966443,
86
+ "eval_f1": 0.8876321254746313,
87
+ "eval_loss": 0.3046204149723053,
88
+ "eval_precision": 0.8891935449502327,
89
+ "eval_recall": 0.889261744966443,
90
+ "eval_runtime": 0.894,
91
+ "eval_samples_per_second": 333.317,
92
+ "eval_steps_per_second": 42.504,
93
+ "step": 130
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8758389261744967,
98
+ "eval_f1": 0.8770158544888631,
99
+ "eval_loss": 0.32443463802337646,
100
+ "eval_precision": 0.8787167286554325,
101
+ "eval_recall": 0.8758389261744967,
102
+ "eval_runtime": 0.9094,
103
+ "eval_samples_per_second": 327.69,
104
+ "eval_steps_per_second": 41.786,
105
+ "step": 149
106
+ },
107
+ {
108
+ "epoch": 8.966442953020135,
109
+ "eval_accuracy": 0.9026845637583892,
110
+ "eval_f1": 0.9018342908983529,
111
+ "eval_loss": 0.2961938679218292,
112
+ "eval_precision": 0.9012011861368664,
113
+ "eval_recall": 0.9026845637583892,
114
+ "eval_runtime": 0.8952,
115
+ "eval_samples_per_second": 332.88,
116
+ "eval_steps_per_second": 42.448,
117
+ "step": 167
118
+ }
119
+ ],
120
+ "logging_steps": 500,
121
+ "max_steps": 216,
122
+ "num_input_tokens_seen": 0,
123
+ "num_train_epochs": 12,
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": 2.43569664576e+16,
147
+ "train_batch_size": 8,
148
+ "trial_name": null,
149
+ "trial_params": null
150
+ }
checkpoint-167/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296be9afae72ab3934d873f0cf92f87ef76899c18b11651de670afb49aa1a5d6
3
+ size 5240
checkpoint-18/config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "1s_asphyxia",
53
+ "1": "1s_hunger",
54
+ "2": "1s_normal",
55
+ "3": "1s_pain"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "1s_asphyxia": "0",
61
+ "1s_hunger": "1",
62
+ "1s_normal": "2",
63
+ "1s_pain": "3"
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.0,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_prob": 0.05,
73
+ "model_type": "hubert",
74
+ "num_attention_heads": 12,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 2,
79
+ "pad_token_id": 0,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.44.2",
82
+ "use_weighted_layer_sum": false,
83
+ "vocab_size": 32
84
+ }