Hugging Face's logo

DunnBC22
/
Is_Vinyl_Scratched_Or_Not

Audio Classification
Transformers
PyTorch
English
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
DunnBC22 commited on
Commit
dc5edbd
·
1 Parent(s): dd8cacd

Upload 85 files

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 +79 -0
  2. checkpoint-105/config.json +125 -0
  3. checkpoint-105/optimizer.pt +3 -0
  4. checkpoint-105/preprocessor_config.json +9 -0
  5. checkpoint-105/pytorch_model.bin +3 -0
  6. checkpoint-105/rng_state.pth +3 -0
  7. checkpoint-105/scheduler.pt +3 -0
  8. checkpoint-105/trainer_state.json +112 -0
  9. checkpoint-105/training_args.bin +3 -0
  10. checkpoint-126/config.json +125 -0
  11. checkpoint-126/optimizer.pt +3 -0
  12. checkpoint-126/preprocessor_config.json +9 -0
  13. checkpoint-126/pytorch_model.bin +3 -0
  14. checkpoint-126/rng_state.pth +3 -0
  15. checkpoint-126/scheduler.pt +3 -0
  16. checkpoint-126/trainer_state.json +130 -0
  17. checkpoint-126/training_args.bin +3 -0
  18. checkpoint-147/config.json +125 -0
  19. checkpoint-147/optimizer.pt +3 -0
  20. checkpoint-147/preprocessor_config.json +9 -0
  21. checkpoint-147/pytorch_model.bin +3 -0
  22. checkpoint-147/rng_state.pth +3 -0
  23. checkpoint-147/scheduler.pt +3 -0
  24. checkpoint-147/trainer_state.json +148 -0
  25. checkpoint-147/training_args.bin +3 -0
  26. checkpoint-168/config.json +125 -0
  27. checkpoint-168/optimizer.pt +3 -0
  28. checkpoint-168/preprocessor_config.json +9 -0
  29. checkpoint-168/pytorch_model.bin +3 -0
  30. checkpoint-168/rng_state.pth +3 -0
  31. checkpoint-168/scheduler.pt +3 -0
  32. checkpoint-168/trainer_state.json +166 -0
  33. checkpoint-168/training_args.bin +3 -0
  34. checkpoint-189/config.json +125 -0
  35. checkpoint-189/optimizer.pt +3 -0
  36. checkpoint-189/preprocessor_config.json +9 -0
  37. checkpoint-189/pytorch_model.bin +3 -0
  38. checkpoint-189/rng_state.pth +3 -0
  39. checkpoint-189/scheduler.pt +3 -0
  40. checkpoint-189/trainer_state.json +184 -0
  41. checkpoint-189/training_args.bin +3 -0
  42. checkpoint-21/config.json +125 -0
  43. checkpoint-21/optimizer.pt +3 -0
  44. checkpoint-21/preprocessor_config.json +9 -0
  45. checkpoint-21/pytorch_model.bin +3 -0
  46. checkpoint-21/rng_state.pth +3 -0
  47. checkpoint-21/scheduler.pt +3 -0
  48. checkpoint-21/trainer_state.json +40 -0
  49. checkpoint-21/training_args.bin +3 -0
  50. checkpoint-210/config.json +125 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - audiofolder
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - recall
11
+ - precision
12
+ model-index:
13
+ - name: wav2vec2-base-is_vinyl_scratched_or_not
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # wav2vec2-base-is_vinyl_scratched_or_not
21
+
22
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.1039
25
+ - Accuracy: 0.9752
26
+ - F1: 0.9638
27
+ - Recall: 0.9576
28
+ - Precision: 0.9700
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
+ - train_batch_size: 32
49
+ - eval_batch_size: 32
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 128
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_ratio: 0.1
56
+ - num_epochs: 10
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
61
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
62
+ | 0.6671 | 0.98 | 21 | 0.6235 | 0.6560 | 0.0 | 0.0 | 0.0 |
63
+ | 0.4954 | 1.98 | 42 | 0.2824 | 0.9417 | 0.9095 | 0.8517 | 0.9757 |
64
+ | 0.2406 | 2.98 | 63 | 0.1755 | 0.9563 | 0.9336 | 0.8941 | 0.9769 |
65
+ | 0.169 | 3.98 | 84 | 0.1545 | 0.9592 | 0.9386 | 0.9068 | 0.9727 |
66
+ | 0.1287 | 4.98 | 105 | 0.1249 | 0.9606 | 0.9407 | 0.9068 | 0.9772 |
67
+ | 0.1102 | 5.98 | 126 | 0.1159 | 0.9723 | 0.9595 | 0.9534 | 0.9657 |
68
+ | 0.0923 | 6.98 | 147 | 0.1073 | 0.9665 | 0.9516 | 0.9576 | 0.9456 |
69
+ | 0.0877 | 7.98 | 168 | 0.1039 | 0.9752 | 0.9638 | 0.9576 | 0.9700 |
70
+ | 0.0807 | 8.98 | 189 | 0.1088 | 0.9679 | 0.9536 | 0.9576 | 0.9496 |
71
+ | 0.0744 | 9.98 | 210 | 0.1041 | 0.9752 | 0.9638 | 0.9576 | 0.9700 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.26.0
77
+ - Pytorch 1.12.1
78
+ - Datasets 2.8.0
79
+ - Tokenizers 0.12.1
checkpoint-105/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-105/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc615861c1c97db60cc54716d8f22865204d98aeaa117729b5e1e2237c70eeb
3
+ size 756671269
checkpoint-105/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-105/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e5b21cd48c3f71dc8de5f13d62125b5f37b1007e5375a55acd0ca79b5d8013
3
+ size 378345555
checkpoint-105/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a2b066fe203264a80066a1515be8c6e3ad6a487e5449a3884608b70bcd6043
3
+ size 13611
checkpoint-105/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802834eb6df0efb5ed147e668771cb8da19ac61fb464214f1fdc4375abceca4e
3
+ size 623
checkpoint-105/trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9406593406593408,
3
+ "best_model_checkpoint": "wav2vec2-base-is_vinyl_scratched_or_not/checkpoint-105",
4
+ "epoch": 4.976744186046512,
5
+ "global_step": 105,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.6901,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.98,
18
+ "learning_rate": 3e-05,
19
+ "loss": 0.6671,
20
+ "step": 21
21
+ },
22
+ {
23
+ "epoch": 0.98,
24
+ "eval_F1": 0.0,
25
+ "eval_Precision": 0.0,
26
+ "eval_Recall": 0.0,
27
+ "eval_accuracy": 0.6559766763848397,
28
+ "eval_loss": 0.6235492825508118,
29
+ "eval_runtime": 1064.9816,
30
+ "eval_samples_per_second": 0.644,
31
+ "eval_steps_per_second": 0.021,
32
+ "step": 21
33
+ },
34
+ {
35
+ "epoch": 1.98,
36
+ "learning_rate": 2.6666666666666667e-05,
37
+ "loss": 0.4954,
38
+ "step": 42
39
+ },
40
+ {
41
+ "epoch": 1.98,
42
+ "eval_F1": 0.9095022624434389,
43
+ "eval_Precision": 0.9757281553398058,
44
+ "eval_Recall": 0.8516949152542372,
45
+ "eval_accuracy": 0.9416909620991254,
46
+ "eval_loss": 0.28244873881340027,
47
+ "eval_runtime": 1042.1602,
48
+ "eval_samples_per_second": 0.658,
49
+ "eval_steps_per_second": 0.021,
50
+ "step": 42
51
+ },
52
+ {
53
+ "epoch": 2.98,
54
+ "learning_rate": 2.3333333333333336e-05,
55
+ "loss": 0.2406,
56
+ "step": 63
57
+ },
58
+ {
59
+ "epoch": 2.98,
60
+ "eval_F1": 0.9336283185840708,
61
+ "eval_Precision": 0.9768518518518519,
62
+ "eval_Recall": 0.8940677966101694,
63
+ "eval_accuracy": 0.956268221574344,
64
+ "eval_loss": 0.17554502189159393,
65
+ "eval_runtime": 1040.1013,
66
+ "eval_samples_per_second": 0.66,
67
+ "eval_steps_per_second": 0.021,
68
+ "step": 63
69
+ },
70
+ {
71
+ "epoch": 3.98,
72
+ "learning_rate": 1.9999999999999998e-05,
73
+ "loss": 0.169,
74
+ "step": 84
75
+ },
76
+ {
77
+ "epoch": 3.98,
78
+ "eval_F1": 0.9385964912280702,
79
+ "eval_Precision": 0.9727272727272728,
80
+ "eval_Recall": 0.9067796610169492,
81
+ "eval_accuracy": 0.9591836734693877,
82
+ "eval_loss": 0.1545204222202301,
83
+ "eval_runtime": 1051.4657,
84
+ "eval_samples_per_second": 0.652,
85
+ "eval_steps_per_second": 0.021,
86
+ "step": 84
87
+ },
88
+ {
89
+ "epoch": 4.98,
90
+ "learning_rate": 1.6666666666666667e-05,
91
+ "loss": 0.1287,
92
+ "step": 105
93
+ },
94
+ {
95
+ "epoch": 4.98,
96
+ "eval_F1": 0.9406593406593408,
97
+ "eval_Precision": 0.9771689497716894,
98
+ "eval_Recall": 0.9067796610169492,
99
+ "eval_accuracy": 0.9606413994169096,
100
+ "eval_loss": 0.1248895600438118,
101
+ "eval_runtime": 1050.486,
102
+ "eval_samples_per_second": 0.653,
103
+ "eval_steps_per_second": 0.021,
104
+ "step": 105
105
+ }
106
+ ],
107
+ "max_steps": 210,
108
+ "num_train_epochs": 10,
109
+ "total_flos": 6.845742942192e+17,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
checkpoint-105/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521181070c5206d39fa1359aeb62443676d9d133bf030a8d47fe7908ee32f60
3
+ size 3503
checkpoint-126/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30404cc39fe15b70d457a896d04a54569e720e2d5c9c274382743bf24c9eb71d
3
+ size 756671269
checkpoint-126/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-126/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32c62d6949a5bc5028c602c846d2f6fb114156a3cd4a624c6bb5f6ec55cc6ba
3
+ size 378345555
checkpoint-126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aeb08987691032a3643895d05d5edf2f416ffcb413a0d620f51c007acb89cf9
3
+ size 13611
checkpoint-126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c22e09d6e80e9e7c82d970fd2f046440b76865cb3bc483ea57adac8a2e0d013
3
+ size 623
checkpoint-126/trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9594882729211086,
3
+ "best_model_checkpoint": "wav2vec2-base-is_vinyl_scratched_or_not/checkpoint-126",
4
+ "epoch": 5.976744186046512,
5
+ "global_step": 126,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.6901,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.98,
18
+ "learning_rate": 3e-05,
19
+ "loss": 0.6671,
20
+ "step": 21
21
+ },
22
+ {
23
+ "epoch": 0.98,
24
+ "eval_F1": 0.0,
25
+ "eval_Precision": 0.0,
26
+ "eval_Recall": 0.0,
27
+ "eval_accuracy": 0.6559766763848397,
28
+ "eval_loss": 0.6235492825508118,
29
+ "eval_runtime": 1064.9816,
30
+ "eval_samples_per_second": 0.644,
31
+ "eval_steps_per_second": 0.021,
32
+ "step": 21
33
+ },
34
+ {
35
+ "epoch": 1.98,
36
+ "learning_rate": 2.6666666666666667e-05,
37
+ "loss": 0.4954,
38
+ "step": 42
39
+ },
40
+ {
41
+ "epoch": 1.98,
42
+ "eval_F1": 0.9095022624434389,
43
+ "eval_Precision": 0.9757281553398058,
44
+ "eval_Recall": 0.8516949152542372,
45
+ "eval_accuracy": 0.9416909620991254,
46
+ "eval_loss": 0.28244873881340027,
47
+ "eval_runtime": 1042.1602,
48
+ "eval_samples_per_second": 0.658,
49
+ "eval_steps_per_second": 0.021,
50
+ "step": 42
51
+ },
52
+ {
53
+ "epoch": 2.98,
54
+ "learning_rate": 2.3333333333333336e-05,
55
+ "loss": 0.2406,
56
+ "step": 63
57
+ },
58
+ {
59
+ "epoch": 2.98,
60
+ "eval_F1": 0.9336283185840708,
61
+ "eval_Precision": 0.9768518518518519,
62
+ "eval_Recall": 0.8940677966101694,
63
+ "eval_accuracy": 0.956268221574344,
64
+ "eval_loss": 0.17554502189159393,
65
+ "eval_runtime": 1040.1013,
66
+ "eval_samples_per_second": 0.66,
67
+ "eval_steps_per_second": 0.021,
68
+ "step": 63
69
+ },
70
+ {
71
+ "epoch": 3.98,
72
+ "learning_rate": 1.9999999999999998e-05,
73
+ "loss": 0.169,
74
+ "step": 84
75
+ },
76
+ {
77
+ "epoch": 3.98,
78
+ "eval_F1": 0.9385964912280702,
79
+ "eval_Precision": 0.9727272727272728,
80
+ "eval_Recall": 0.9067796610169492,
81
+ "eval_accuracy": 0.9591836734693877,
82
+ "eval_loss": 0.1545204222202301,
83
+ "eval_runtime": 1051.4657,
84
+ "eval_samples_per_second": 0.652,
85
+ "eval_steps_per_second": 0.021,
86
+ "step": 84
87
+ },
88
+ {
89
+ "epoch": 4.98,
90
+ "learning_rate": 1.6666666666666667e-05,
91
+ "loss": 0.1287,
92
+ "step": 105
93
+ },
94
+ {
95
+ "epoch": 4.98,
96
+ "eval_F1": 0.9406593406593408,
97
+ "eval_Precision": 0.9771689497716894,
98
+ "eval_Recall": 0.9067796610169492,
99
+ "eval_accuracy": 0.9606413994169096,
100
+ "eval_loss": 0.1248895600438118,
101
+ "eval_runtime": 1050.486,
102
+ "eval_samples_per_second": 0.653,
103
+ "eval_steps_per_second": 0.021,
104
+ "step": 105
105
+ },
106
+ {
107
+ "epoch": 5.98,
108
+ "learning_rate": 1.3333333333333333e-05,
109
+ "loss": 0.1102,
110
+ "step": 126
111
+ },
112
+ {
113
+ "epoch": 5.98,
114
+ "eval_F1": 0.9594882729211086,
115
+ "eval_Precision": 0.9656652360515021,
116
+ "eval_Recall": 0.9533898305084746,
117
+ "eval_accuracy": 0.9723032069970845,
118
+ "eval_loss": 0.11587227135896683,
119
+ "eval_runtime": 1049.2012,
120
+ "eval_samples_per_second": 0.654,
121
+ "eval_steps_per_second": 0.021,
122
+ "step": 126
123
+ }
124
+ ],
125
+ "max_steps": 210,
126
+ "num_train_epochs": 10,
127
+ "total_flos": 8.2148915306304e+17,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
checkpoint-126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521181070c5206d39fa1359aeb62443676d9d133bf030a8d47fe7908ee32f60
3
+ size 3503
checkpoint-147/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-147/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8792a4eb875c1716cddbb0b8ef83d84c280350a6dd26c8e072b8fd251d1f04
3
+ size 756671269
checkpoint-147/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-147/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3255ba90fd5778c017bd790e559b1444d916354bf63a360fc7db43c435cd83
3
+ size 378345555
checkpoint-147/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82889f72e9194f8f2e54e48553d15a3facdacb0c7e99f06a72b71f2e4f3fb24
3
+ size 13611
checkpoint-147/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f575b7a521d42834c25781b03ebcb41b842dae0e69331794ec5b689a01173a
3
+ size 623
checkpoint-147/trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9594882729211086,
3
+ "best_model_checkpoint": "wav2vec2-base-is_vinyl_scratched_or_not/checkpoint-126",
4
+ "epoch": 6.976744186046512,
5
+ "global_step": 147,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.6901,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.98,
18
+ "learning_rate": 3e-05,
19
+ "loss": 0.6671,
20
+ "step": 21
21
+ },
22
+ {
23
+ "epoch": 0.98,
24
+ "eval_F1": 0.0,
25
+ "eval_Precision": 0.0,
26
+ "eval_Recall": 0.0,
27
+ "eval_accuracy": 0.6559766763848397,
28
+ "eval_loss": 0.6235492825508118,
29
+ "eval_runtime": 1064.9816,
30
+ "eval_samples_per_second": 0.644,
31
+ "eval_steps_per_second": 0.021,
32
+ "step": 21
33
+ },
34
+ {
35
+ "epoch": 1.98,
36
+ "learning_rate": 2.6666666666666667e-05,
37
+ "loss": 0.4954,
38
+ "step": 42
39
+ },
40
+ {
41
+ "epoch": 1.98,
42
+ "eval_F1": 0.9095022624434389,
43
+ "eval_Precision": 0.9757281553398058,
44
+ "eval_Recall": 0.8516949152542372,
45
+ "eval_accuracy": 0.9416909620991254,
46
+ "eval_loss": 0.28244873881340027,
47
+ "eval_runtime": 1042.1602,
48
+ "eval_samples_per_second": 0.658,
49
+ "eval_steps_per_second": 0.021,
50
+ "step": 42
51
+ },
52
+ {
53
+ "epoch": 2.98,
54
+ "learning_rate": 2.3333333333333336e-05,
55
+ "loss": 0.2406,
56
+ "step": 63
57
+ },
58
+ {
59
+ "epoch": 2.98,
60
+ "eval_F1": 0.9336283185840708,
61
+ "eval_Precision": 0.9768518518518519,
62
+ "eval_Recall": 0.8940677966101694,
63
+ "eval_accuracy": 0.956268221574344,
64
+ "eval_loss": 0.17554502189159393,
65
+ "eval_runtime": 1040.1013,
66
+ "eval_samples_per_second": 0.66,
67
+ "eval_steps_per_second": 0.021,
68
+ "step": 63
69
+ },
70
+ {
71
+ "epoch": 3.98,
72
+ "learning_rate": 1.9999999999999998e-05,
73
+ "loss": 0.169,
74
+ "step": 84
75
+ },
76
+ {
77
+ "epoch": 3.98,
78
+ "eval_F1": 0.9385964912280702,
79
+ "eval_Precision": 0.9727272727272728,
80
+ "eval_Recall": 0.9067796610169492,
81
+ "eval_accuracy": 0.9591836734693877,
82
+ "eval_loss": 0.1545204222202301,
83
+ "eval_runtime": 1051.4657,
84
+ "eval_samples_per_second": 0.652,
85
+ "eval_steps_per_second": 0.021,
86
+ "step": 84
87
+ },
88
+ {
89
+ "epoch": 4.98,
90
+ "learning_rate": 1.6666666666666667e-05,
91
+ "loss": 0.1287,
92
+ "step": 105
93
+ },
94
+ {
95
+ "epoch": 4.98,
96
+ "eval_F1": 0.9406593406593408,
97
+ "eval_Precision": 0.9771689497716894,
98
+ "eval_Recall": 0.9067796610169492,
99
+ "eval_accuracy": 0.9606413994169096,
100
+ "eval_loss": 0.1248895600438118,
101
+ "eval_runtime": 1050.486,
102
+ "eval_samples_per_second": 0.653,
103
+ "eval_steps_per_second": 0.021,
104
+ "step": 105
105
+ },
106
+ {
107
+ "epoch": 5.98,
108
+ "learning_rate": 1.3333333333333333e-05,
109
+ "loss": 0.1102,
110
+ "step": 126
111
+ },
112
+ {
113
+ "epoch": 5.98,
114
+ "eval_F1": 0.9594882729211086,
115
+ "eval_Precision": 0.9656652360515021,
116
+ "eval_Recall": 0.9533898305084746,
117
+ "eval_accuracy": 0.9723032069970845,
118
+ "eval_loss": 0.11587227135896683,
119
+ "eval_runtime": 1049.2012,
120
+ "eval_samples_per_second": 0.654,
121
+ "eval_steps_per_second": 0.021,
122
+ "step": 126
123
+ },
124
+ {
125
+ "epoch": 6.98,
126
+ "learning_rate": 9.999999999999999e-06,
127
+ "loss": 0.0923,
128
+ "step": 147
129
+ },
130
+ {
131
+ "epoch": 6.98,
132
+ "eval_F1": 0.9515789473684211,
133
+ "eval_Precision": 0.9456066945606695,
134
+ "eval_Recall": 0.9576271186440678,
135
+ "eval_accuracy": 0.9664723032069971,
136
+ "eval_loss": 0.10729651153087616,
137
+ "eval_runtime": 1059.4975,
138
+ "eval_samples_per_second": 0.647,
139
+ "eval_steps_per_second": 0.021,
140
+ "step": 147
141
+ }
142
+ ],
143
+ "max_steps": 210,
144
+ "num_train_epochs": 10,
145
+ "total_flos": 9.5840401190688e+17,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }
checkpoint-147/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521181070c5206d39fa1359aeb62443676d9d133bf030a8d47fe7908ee32f60
3
+ size 3503
checkpoint-168/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-168/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3efb950e1d52afb01b74807bd334aadda26ae9db22d6814e2dd8340f4415f3
3
+ size 756671269
checkpoint-168/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-168/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d80feebf75b9add887b3409fea764a26b226005fc477c13b47098cca4579b04
3
+ size 378345555
checkpoint-168/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4348501b22a26ac1aeb2e86bd788289116344a48402648de3777819ec84c429
3
+ size 13611
checkpoint-168/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4660b0d5db40788f4a079cb632965b97fb6cb598256ca600a122531f32b5c711
3
+ size 623
checkpoint-168/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9637526652452025,
3
+ "best_model_checkpoint": "wav2vec2-base-is_vinyl_scratched_or_not/checkpoint-168",
4
+ "epoch": 7.976744186046512,
5
+ "global_step": 168,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.6901,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.98,
18
+ "learning_rate": 3e-05,
19
+ "loss": 0.6671,
20
+ "step": 21
21
+ },
22
+ {
23
+ "epoch": 0.98,
24
+ "eval_F1": 0.0,
25
+ "eval_Precision": 0.0,
26
+ "eval_Recall": 0.0,
27
+ "eval_accuracy": 0.6559766763848397,
28
+ "eval_loss": 0.6235492825508118,
29
+ "eval_runtime": 1064.9816,
30
+ "eval_samples_per_second": 0.644,
31
+ "eval_steps_per_second": 0.021,
32
+ "step": 21
33
+ },
34
+ {
35
+ "epoch": 1.98,
36
+ "learning_rate": 2.6666666666666667e-05,
37
+ "loss": 0.4954,
38
+ "step": 42
39
+ },
40
+ {
41
+ "epoch": 1.98,
42
+ "eval_F1": 0.9095022624434389,
43
+ "eval_Precision": 0.9757281553398058,
44
+ "eval_Recall": 0.8516949152542372,
45
+ "eval_accuracy": 0.9416909620991254,
46
+ "eval_loss": 0.28244873881340027,
47
+ "eval_runtime": 1042.1602,
48
+ "eval_samples_per_second": 0.658,
49
+ "eval_steps_per_second": 0.021,
50
+ "step": 42
51
+ },
52
+ {
53
+ "epoch": 2.98,
54
+ "learning_rate": 2.3333333333333336e-05,
55
+ "loss": 0.2406,
56
+ "step": 63
57
+ },
58
+ {
59
+ "epoch": 2.98,
60
+ "eval_F1": 0.9336283185840708,
61
+ "eval_Precision": 0.9768518518518519,
62
+ "eval_Recall": 0.8940677966101694,
63
+ "eval_accuracy": 0.956268221574344,
64
+ "eval_loss": 0.17554502189159393,
65
+ "eval_runtime": 1040.1013,
66
+ "eval_samples_per_second": 0.66,
67
+ "eval_steps_per_second": 0.021,
68
+ "step": 63
69
+ },
70
+ {
71
+ "epoch": 3.98,
72
+ "learning_rate": 1.9999999999999998e-05,
73
+ "loss": 0.169,
74
+ "step": 84
75
+ },
76
+ {
77
+ "epoch": 3.98,
78
+ "eval_F1": 0.9385964912280702,
79
+ "eval_Precision": 0.9727272727272728,
80
+ "eval_Recall": 0.9067796610169492,
81
+ "eval_accuracy": 0.9591836734693877,
82
+ "eval_loss": 0.1545204222202301,
83
+ "eval_runtime": 1051.4657,
84
+ "eval_samples_per_second": 0.652,
85
+ "eval_steps_per_second": 0.021,
86
+ "step": 84
87
+ },
88
+ {
89
+ "epoch": 4.98,
90
+ "learning_rate": 1.6666666666666667e-05,
91
+ "loss": 0.1287,
92
+ "step": 105
93
+ },
94
+ {
95
+ "epoch": 4.98,
96
+ "eval_F1": 0.9406593406593408,
97
+ "eval_Precision": 0.9771689497716894,
98
+ "eval_Recall": 0.9067796610169492,
99
+ "eval_accuracy": 0.9606413994169096,
100
+ "eval_loss": 0.1248895600438118,
101
+ "eval_runtime": 1050.486,
102
+ "eval_samples_per_second": 0.653,
103
+ "eval_steps_per_second": 0.021,
104
+ "step": 105
105
+ },
106
+ {
107
+ "epoch": 5.98,
108
+ "learning_rate": 1.3333333333333333e-05,
109
+ "loss": 0.1102,
110
+ "step": 126
111
+ },
112
+ {
113
+ "epoch": 5.98,
114
+ "eval_F1": 0.9594882729211086,
115
+ "eval_Precision": 0.9656652360515021,
116
+ "eval_Recall": 0.9533898305084746,
117
+ "eval_accuracy": 0.9723032069970845,
118
+ "eval_loss": 0.11587227135896683,
119
+ "eval_runtime": 1049.2012,
120
+ "eval_samples_per_second": 0.654,
121
+ "eval_steps_per_second": 0.021,
122
+ "step": 126
123
+ },
124
+ {
125
+ "epoch": 6.98,
126
+ "learning_rate": 9.999999999999999e-06,
127
+ "loss": 0.0923,
128
+ "step": 147
129
+ },
130
+ {
131
+ "epoch": 6.98,
132
+ "eval_F1": 0.9515789473684211,
133
+ "eval_Precision": 0.9456066945606695,
134
+ "eval_Recall": 0.9576271186440678,
135
+ "eval_accuracy": 0.9664723032069971,
136
+ "eval_loss": 0.10729651153087616,
137
+ "eval_runtime": 1059.4975,
138
+ "eval_samples_per_second": 0.647,
139
+ "eval_steps_per_second": 0.021,
140
+ "step": 147
141
+ },
142
+ {
143
+ "epoch": 7.98,
144
+ "learning_rate": 6.666666666666667e-06,
145
+ "loss": 0.0877,
146
+ "step": 168
147
+ },
148
+ {
149
+ "epoch": 7.98,
150
+ "eval_F1": 0.9637526652452025,
151
+ "eval_Precision": 0.9699570815450643,
152
+ "eval_Recall": 0.9576271186440678,
153
+ "eval_accuracy": 0.9752186588921283,
154
+ "eval_loss": 0.10392837971448898,
155
+ "eval_runtime": 1046.4548,
156
+ "eval_samples_per_second": 0.656,
157
+ "eval_steps_per_second": 0.021,
158
+ "step": 168
159
+ }
160
+ ],
161
+ "max_steps": 210,
162
+ "num_train_epochs": 10,
163
+ "total_flos": 1.09531887075072e+18,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
checkpoint-168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521181070c5206d39fa1359aeb62443676d9d133bf030a8d47fe7908ee32f60
3
+ size 3503
checkpoint-189/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-189/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ef3cb8889aaaab5a453bf47370bf98789ed72760255063c98e437298875d82
3
+ size 756671269
checkpoint-189/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-189/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8657ad0496958f12263ab116c4668fecd090d248dad239bb4725f83bb444bcb2
3
+ size 378345555
checkpoint-189/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e80e4564843ebfeac09ae18cd3b55e53b0138af482143fcd87c1db6d4d2623
3
+ size 13611
checkpoint-189/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e491ae4f90e3635a94ed7f571a9260440304eccbe49682f12a95646aaeb21c4
3
+ size 623
checkpoint-189/trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9637526652452025,
3
+ "best_model_checkpoint": "wav2vec2-base-is_vinyl_scratched_or_not/checkpoint-168",
4
+ "epoch": 8.976744186046512,
5
+ "global_step": 189,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.6901,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.98,
18
+ "learning_rate": 3e-05,
19
+ "loss": 0.6671,
20
+ "step": 21
21
+ },
22
+ {
23
+ "epoch": 0.98,
24
+ "eval_F1": 0.0,
25
+ "eval_Precision": 0.0,
26
+ "eval_Recall": 0.0,
27
+ "eval_accuracy": 0.6559766763848397,
28
+ "eval_loss": 0.6235492825508118,
29
+ "eval_runtime": 1064.9816,
30
+ "eval_samples_per_second": 0.644,
31
+ "eval_steps_per_second": 0.021,
32
+ "step": 21
33
+ },
34
+ {
35
+ "epoch": 1.98,
36
+ "learning_rate": 2.6666666666666667e-05,
37
+ "loss": 0.4954,
38
+ "step": 42
39
+ },
40
+ {
41
+ "epoch": 1.98,
42
+ "eval_F1": 0.9095022624434389,
43
+ "eval_Precision": 0.9757281553398058,
44
+ "eval_Recall": 0.8516949152542372,
45
+ "eval_accuracy": 0.9416909620991254,
46
+ "eval_loss": 0.28244873881340027,
47
+ "eval_runtime": 1042.1602,
48
+ "eval_samples_per_second": 0.658,
49
+ "eval_steps_per_second": 0.021,
50
+ "step": 42
51
+ },
52
+ {
53
+ "epoch": 2.98,
54
+ "learning_rate": 2.3333333333333336e-05,
55
+ "loss": 0.2406,
56
+ "step": 63
57
+ },
58
+ {
59
+ "epoch": 2.98,
60
+ "eval_F1": 0.9336283185840708,
61
+ "eval_Precision": 0.9768518518518519,
62
+ "eval_Recall": 0.8940677966101694,
63
+ "eval_accuracy": 0.956268221574344,
64
+ "eval_loss": 0.17554502189159393,
65
+ "eval_runtime": 1040.1013,
66
+ "eval_samples_per_second": 0.66,
67
+ "eval_steps_per_second": 0.021,
68
+ "step": 63
69
+ },
70
+ {
71
+ "epoch": 3.98,
72
+ "learning_rate": 1.9999999999999998e-05,
73
+ "loss": 0.169,
74
+ "step": 84
75
+ },
76
+ {
77
+ "epoch": 3.98,
78
+ "eval_F1": 0.9385964912280702,
79
+ "eval_Precision": 0.9727272727272728,
80
+ "eval_Recall": 0.9067796610169492,
81
+ "eval_accuracy": 0.9591836734693877,
82
+ "eval_loss": 0.1545204222202301,
83
+ "eval_runtime": 1051.4657,
84
+ "eval_samples_per_second": 0.652,
85
+ "eval_steps_per_second": 0.021,
86
+ "step": 84
87
+ },
88
+ {
89
+ "epoch": 4.98,
90
+ "learning_rate": 1.6666666666666667e-05,
91
+ "loss": 0.1287,
92
+ "step": 105
93
+ },
94
+ {
95
+ "epoch": 4.98,
96
+ "eval_F1": 0.9406593406593408,
97
+ "eval_Precision": 0.9771689497716894,
98
+ "eval_Recall": 0.9067796610169492,
99
+ "eval_accuracy": 0.9606413994169096,
100
+ "eval_loss": 0.1248895600438118,
101
+ "eval_runtime": 1050.486,
102
+ "eval_samples_per_second": 0.653,
103
+ "eval_steps_per_second": 0.021,
104
+ "step": 105
105
+ },
106
+ {
107
+ "epoch": 5.98,
108
+ "learning_rate": 1.3333333333333333e-05,
109
+ "loss": 0.1102,
110
+ "step": 126
111
+ },
112
+ {
113
+ "epoch": 5.98,
114
+ "eval_F1": 0.9594882729211086,
115
+ "eval_Precision": 0.9656652360515021,
116
+ "eval_Recall": 0.9533898305084746,
117
+ "eval_accuracy": 0.9723032069970845,
118
+ "eval_loss": 0.11587227135896683,
119
+ "eval_runtime": 1049.2012,
120
+ "eval_samples_per_second": 0.654,
121
+ "eval_steps_per_second": 0.021,
122
+ "step": 126
123
+ },
124
+ {
125
+ "epoch": 6.98,
126
+ "learning_rate": 9.999999999999999e-06,
127
+ "loss": 0.0923,
128
+ "step": 147
129
+ },
130
+ {
131
+ "epoch": 6.98,
132
+ "eval_F1": 0.9515789473684211,
133
+ "eval_Precision": 0.9456066945606695,
134
+ "eval_Recall": 0.9576271186440678,
135
+ "eval_accuracy": 0.9664723032069971,
136
+ "eval_loss": 0.10729651153087616,
137
+ "eval_runtime": 1059.4975,
138
+ "eval_samples_per_second": 0.647,
139
+ "eval_steps_per_second": 0.021,
140
+ "step": 147
141
+ },
142
+ {
143
+ "epoch": 7.98,
144
+ "learning_rate": 6.666666666666667e-06,
145
+ "loss": 0.0877,
146
+ "step": 168
147
+ },
148
+ {
149
+ "epoch": 7.98,
150
+ "eval_F1": 0.9637526652452025,
151
+ "eval_Precision": 0.9699570815450643,
152
+ "eval_Recall": 0.9576271186440678,
153
+ "eval_accuracy": 0.9752186588921283,
154
+ "eval_loss": 0.10392837971448898,
155
+ "eval_runtime": 1046.4548,
156
+ "eval_samples_per_second": 0.656,
157
+ "eval_steps_per_second": 0.021,
158
+ "step": 168
159
+ },
160
+ {
161
+ "epoch": 8.98,
162
+ "learning_rate": 3.3333333333333333e-06,
163
+ "loss": 0.0807,
164
+ "step": 189
165
+ },
166
+ {
167
+ "epoch": 8.98,
168
+ "eval_F1": 0.9535864978902954,
169
+ "eval_Precision": 0.9495798319327731,
170
+ "eval_Recall": 0.9576271186440678,
171
+ "eval_accuracy": 0.967930029154519,
172
+ "eval_loss": 0.1087886393070221,
173
+ "eval_runtime": 1049.1807,
174
+ "eval_samples_per_second": 0.654,
175
+ "eval_steps_per_second": 0.021,
176
+ "step": 189
177
+ }
178
+ ],
179
+ "max_steps": 210,
180
+ "num_train_epochs": 10,
181
+ "total_flos": 1.23223372959456e+18,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }
checkpoint-189/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521181070c5206d39fa1359aeb62443676d9d133bf030a8d47fe7908ee32f60
3
+ size 3503
checkpoint-21/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d717d50ea851bbd0760c0ae423052eefdaee77dd648084a79f044065794371
3
+ size 756671269
checkpoint-21/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-21/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0371786eca2dbe97f5e2252e9fde629e17ec822d1238935c2d5925d3698ea23
3
+ size 378345555
checkpoint-21/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e53348e6c5c6bfde5399afe15ee8fc9cc0fe4f71f4fcaf81a61b7ef10eccb9
3
+ size 13611
checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01863609429bdde21eb3473e4cf95739e54347819109a4d54c5a249f872b4fc6
3
+ size 623
checkpoint-21/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "wav2vec2-base-is_vinyl_scratched_or_not/checkpoint-21",
4
+ "epoch": 0.9767441860465116,
5
+ "global_step": 21,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 0.6901,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.98,
18
+ "learning_rate": 3e-05,
19
+ "loss": 0.6671,
20
+ "step": 21
21
+ },
22
+ {
23
+ "epoch": 0.98,
24
+ "eval_F1": 0.0,
25
+ "eval_Precision": 0.0,
26
+ "eval_Recall": 0.0,
27
+ "eval_accuracy": 0.6559766763848397,
28
+ "eval_loss": 0.6235492825508118,
29
+ "eval_runtime": 1064.9816,
30
+ "eval_samples_per_second": 0.644,
31
+ "eval_steps_per_second": 0.021,
32
+ "step": 21
33
+ }
34
+ ],
35
+ "max_steps": 210,
36
+ "num_train_epochs": 10,
37
+ "total_flos": 1.3691485884384e+17,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521181070c5206d39fa1359aeb62443676d9d133bf030a8d47fe7908ee32f60
3
+ size 3503
checkpoint-210/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": 0,
60
+ "1": 1
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "0": "0",
66
+ "1": "1"
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.0,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.26.0",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }