Hugging Face's logo

alonb19
/
EF-instruments

PyTorch
TensorBoard
wav2vec2
Model card Files
xet
 Metrics Community
alonb19 commited on
Commit
6d1166b
·
verified ·
1 Parent(s): df5b1d0

Upload folder using huggingface_hub

Browse files
Files changed (34) hide show
  1. checkpoint-120/config.json +119 -0
  2. checkpoint-120/optimizer.pt +3 -0
  3. checkpoint-120/preprocessor_config.json +9 -0
  4. checkpoint-120/pytorch_model.bin +3 -0
  5. checkpoint-120/rng_state.pth +3 -0
  6. checkpoint-120/scaler.pt +3 -0
  7. checkpoint-120/scheduler.pt +3 -0
  8. checkpoint-120/trainer_state.json +106 -0
  9. checkpoint-120/training_args.bin +3 -0
  10. checkpoint-180/config.json +119 -0
  11. checkpoint-180/optimizer.pt +3 -0
  12. checkpoint-180/preprocessor_config.json +9 -0
  13. checkpoint-180/pytorch_model.bin +3 -0
  14. checkpoint-180/rng_state.pth +3 -0
  15. checkpoint-180/scaler.pt +3 -0
  16. checkpoint-180/scheduler.pt +3 -0
  17. checkpoint-180/trainer_state.json +151 -0
  18. checkpoint-180/training_args.bin +3 -0
  19. checkpoint-60/config.json +119 -0
  20. checkpoint-60/optimizer.pt +3 -0
  21. checkpoint-60/preprocessor_config.json +9 -0
  22. checkpoint-60/pytorch_model.bin +3 -0
  23. checkpoint-60/rng_state.pth +3 -0
  24. checkpoint-60/scaler.pt +3 -0
  25. checkpoint-60/scheduler.pt +3 -0
  26. checkpoint-60/trainer_state.json +61 -0
  27. checkpoint-60/training_args.bin +3 -0
  28. config.json +119 -0
  29. preprocessor_config.json +9 -0
  30. pytorch_model.bin +3 -0
  31. runs/Jul12_22-57-29_bfd727bb6ba4/1752361052.536027/events.out.tfevents.1752361052.bfd727bb6ba4.23677.1 +3 -0
  32. runs/Jul12_22-57-29_bfd727bb6ba4/events.out.tfevents.1752361052.bfd727bb6ba4.23677.0 +3 -0
  33. runs/Jul12_22-57-29_bfd727bb6ba4/events.out.tfevents.1752361168.bfd727bb6ba4.23677.2 +3 -0
  34. training_args.bin +3 -0
checkpoint-120/config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Sound_Guitar",
62
+ "1": "Sound_Drum",
63
+ "2": "Sound_Piano"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "label2id": {
68
+ "Sound_Drum": 1,
69
+ "Sound_Guitar": 0,
70
+ "Sound_Piano": 2
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.05,
80
+ "model_type": "wav2vec2",
81
+ "num_adapter_layers": 3,
82
+ "num_attention_heads": 12,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 12,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 768,
91
+ "pad_token_id": 0,
92
+ "proj_codevector_dim": 256,
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.28.1",
116
+ "use_weighted_layer_sum": false,
117
+ "vocab_size": 32,
118
+ "xvector_output_dim": 512
119
+ }
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe97c2644def2a416b1c786d18a13a4ef72f30866a43b2bcc21240ed18ca79c
3
+ size 756681210
checkpoint-120/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-120/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484b52050e234d58cf1beab232001ce415c6e1cf336999794523eea9a7bfa37f
3
+ size 378351910
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494782ee4a285e29d684de4fbb4731946c46eef9cce7d7bf6223fe5b1701c173
3
+ size 14308
checkpoint-120/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ad171fdeeb5981184a7616fc04c7a043642c65bcc0bacf0a405d307b070ff3
3
+ size 988
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3262be4266ae83ca8181f9600ae908ec6cd2709d6476b03a13a261ab035f045
3
+ size 1064
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9416666666666667,
3
+ "best_model_checkpoint": "musical_instrument_detection/checkpoint-120",
4
+ "epoch": 2.0,
5
+ "global_step": 120,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 1.388888888888889e-05,
13
+ "loss": 1.0972,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.33,
18
+ "learning_rate": 4.166666666666667e-05,
19
+ "loss": 1.0918,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.5,
24
+ "learning_rate": 4.845679012345679e-05,
25
+ "loss": 1.0605,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.67,
30
+ "learning_rate": 4.5370370370370374e-05,
31
+ "loss": 0.9438,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.83,
36
+ "learning_rate": 4.2283950617283955e-05,
37
+ "loss": 0.836,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "learning_rate": 3.9197530864197535e-05,
43
+ "loss": 0.7532,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.8875,
49
+ "eval_loss": 0.5960062742233276,
50
+ "eval_runtime": 0.9405,
51
+ "eval_samples_per_second": 255.183,
52
+ "eval_steps_per_second": 15.949,
53
+ "step": 60
54
+ },
55
+ {
56
+ "epoch": 1.17,
57
+ "learning_rate": 3.611111111111111e-05,
58
+ "loss": 0.6293,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.33,
63
+ "learning_rate": 3.30246913580247e-05,
64
+ "loss": 0.4708,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.5,
69
+ "learning_rate": 2.993827160493827e-05,
70
+ "loss": 0.4269,
71
+ "step": 90
72
+ },
73
+ {
74
+ "epoch": 1.67,
75
+ "learning_rate": 2.6851851851851855e-05,
76
+ "loss": 0.3675,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 1.83,
81
+ "learning_rate": 2.3765432098765433e-05,
82
+ "loss": 0.3502,
83
+ "step": 110
84
+ },
85
+ {
86
+ "epoch": 2.0,
87
+ "learning_rate": 2.0679012345679014e-05,
88
+ "loss": 0.4161,
89
+ "step": 120
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "eval_accuracy": 0.9416666666666667,
94
+ "eval_loss": 0.25962144136428833,
95
+ "eval_runtime": 0.9356,
96
+ "eval_samples_per_second": 256.529,
97
+ "eval_steps_per_second": 16.033,
98
+ "step": 120
99
+ }
100
+ ],
101
+ "max_steps": 180,
102
+ "num_train_epochs": 3,
103
+ "total_flos": 1.743102203904e+17,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed46c74c84ed7c649b9a6c9f49ebc80fd9e19c4d55f5e4b624542952595b972
3
+ size 4088
checkpoint-180/config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Sound_Guitar",
62
+ "1": "Sound_Drum",
63
+ "2": "Sound_Piano"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "label2id": {
68
+ "Sound_Drum": 1,
69
+ "Sound_Guitar": 0,
70
+ "Sound_Piano": 2
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.05,
80
+ "model_type": "wav2vec2",
81
+ "num_adapter_layers": 3,
82
+ "num_attention_heads": 12,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 12,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 768,
91
+ "pad_token_id": 0,
92
+ "proj_codevector_dim": 256,
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.28.1",
116
+ "use_weighted_layer_sum": false,
117
+ "vocab_size": 32,
118
+ "xvector_output_dim": 512
119
+ }
checkpoint-180/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab8647512cdb0732612b59993a9c08bbe61fbb52ef20937c7bda7ab8a3c4a2c
3
+ size 756681210
checkpoint-180/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-180/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84a5098ba7544003f7a1683d452bc3196d0f3d8a043afb34bd627a539fcdab4
3
+ size 378351910
checkpoint-180/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a393518595c2b1e22482ad483a0a26b15b1bf21167894265d3bca445a051eb20
3
+ size 14308
checkpoint-180/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e679a2175adbec7edc256dad7efaaf776a9e59dc37ee0b315d71f04f62852418
3
+ size 988
checkpoint-180/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d7e97d9e74f4b6eed73d143087c7e22b9240f7ef0fd758e62e5027e9aebf90
3
+ size 1064
checkpoint-180/trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.975,
3
+ "best_model_checkpoint": "musical_instrument_detection/checkpoint-180",
4
+ "epoch": 3.0,
5
+ "global_step": 180,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 1.388888888888889e-05,
13
+ "loss": 1.0972,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.33,
18
+ "learning_rate": 4.166666666666667e-05,
19
+ "loss": 1.0918,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.5,
24
+ "learning_rate": 4.845679012345679e-05,
25
+ "loss": 1.0605,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.67,
30
+ "learning_rate": 4.5370370370370374e-05,
31
+ "loss": 0.9438,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.83,
36
+ "learning_rate": 4.2283950617283955e-05,
37
+ "loss": 0.836,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "learning_rate": 3.9197530864197535e-05,
43
+ "loss": 0.7532,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.8875,
49
+ "eval_loss": 0.5960062742233276,
50
+ "eval_runtime": 0.9405,
51
+ "eval_samples_per_second": 255.183,
52
+ "eval_steps_per_second": 15.949,
53
+ "step": 60
54
+ },
55
+ {
56
+ "epoch": 1.17,
57
+ "learning_rate": 3.611111111111111e-05,
58
+ "loss": 0.6293,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.33,
63
+ "learning_rate": 3.30246913580247e-05,
64
+ "loss": 0.4708,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.5,
69
+ "learning_rate": 2.993827160493827e-05,
70
+ "loss": 0.4269,
71
+ "step": 90
72
+ },
73
+ {
74
+ "epoch": 1.67,
75
+ "learning_rate": 2.6851851851851855e-05,
76
+ "loss": 0.3675,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 1.83,
81
+ "learning_rate": 2.3765432098765433e-05,
82
+ "loss": 0.3502,
83
+ "step": 110
84
+ },
85
+ {
86
+ "epoch": 2.0,
87
+ "learning_rate": 2.0679012345679014e-05,
88
+ "loss": 0.4161,
89
+ "step": 120
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "eval_accuracy": 0.9416666666666667,
94
+ "eval_loss": 0.25962144136428833,
95
+ "eval_runtime": 0.9356,
96
+ "eval_samples_per_second": 256.529,
97
+ "eval_steps_per_second": 16.033,
98
+ "step": 120
99
+ },
100
+ {
101
+ "epoch": 2.17,
102
+ "learning_rate": 1.7592592592592595e-05,
103
+ "loss": 0.225,
104
+ "step": 130
105
+ },
106
+ {
107
+ "epoch": 2.33,
108
+ "learning_rate": 1.4506172839506174e-05,
109
+ "loss": 0.2765,
110
+ "step": 140
111
+ },
112
+ {
113
+ "epoch": 2.5,
114
+ "learning_rate": 1.1419753086419753e-05,
115
+ "loss": 0.3095,
116
+ "step": 150
117
+ },
118
+ {
119
+ "epoch": 2.67,
120
+ "learning_rate": 8.333333333333334e-06,
121
+ "loss": 0.2009,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 2.83,
126
+ "learning_rate": 5.246913580246914e-06,
127
+ "loss": 0.1703,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 3.0,
132
+ "learning_rate": 2.1604938271604937e-06,
133
+ "loss": 0.1493,
134
+ "step": 180
135
+ },
136
+ {
137
+ "epoch": 3.0,
138
+ "eval_accuracy": 0.975,
139
+ "eval_loss": 0.13954709470272064,
140
+ "eval_runtime": 0.9216,
141
+ "eval_samples_per_second": 260.407,
142
+ "eval_steps_per_second": 16.275,
143
+ "step": 180
144
+ }
145
+ ],
146
+ "max_steps": 180,
147
+ "num_train_epochs": 3,
148
+ "total_flos": 2.614653305856e+17,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }
checkpoint-180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed46c74c84ed7c649b9a6c9f49ebc80fd9e19c4d55f5e4b624542952595b972
3
+ size 4088
checkpoint-60/config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Sound_Guitar",
62
+ "1": "Sound_Drum",
63
+ "2": "Sound_Piano"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "label2id": {
68
+ "Sound_Drum": 1,
69
+ "Sound_Guitar": 0,
70
+ "Sound_Piano": 2
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.05,
80
+ "model_type": "wav2vec2",
81
+ "num_adapter_layers": 3,
82
+ "num_attention_heads": 12,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 12,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 768,
91
+ "pad_token_id": 0,
92
+ "proj_codevector_dim": 256,
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.28.1",
116
+ "use_weighted_layer_sum": false,
117
+ "vocab_size": 32,
118
+ "xvector_output_dim": 512
119
+ }
checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3bb8ef98749b35ec98fd8d808f5a6a3107a8153c96039abc8482d6af5632e6
3
+ size 756681210
checkpoint-60/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-60/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4270afad8f40474d948e997d69a769c39ccb036b693c2656918745c30fba1a
3
+ size 378351910
checkpoint-60/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545e6b4fad1c235258ad867951894f44548e156015ba9af0a83e7236a1f66d0e
3
+ size 14244
checkpoint-60/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4335b81860a0a26ae7592522e3efff4b13a7a7f17bd51f4b6364a7af1ada4d4
3
+ size 988
checkpoint-60/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990c3eabe6c481f059a179cea70520697f504204b685ea1bd5f54833046981da
3
+ size 1064
checkpoint-60/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8875,
3
+ "best_model_checkpoint": "musical_instrument_detection/checkpoint-60",
4
+ "epoch": 1.0,
5
+ "global_step": 60,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 1.388888888888889e-05,
13
+ "loss": 1.0972,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.33,
18
+ "learning_rate": 4.166666666666667e-05,
19
+ "loss": 1.0918,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.5,
24
+ "learning_rate": 4.845679012345679e-05,
25
+ "loss": 1.0605,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.67,
30
+ "learning_rate": 4.5370370370370374e-05,
31
+ "loss": 0.9438,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.83,
36
+ "learning_rate": 4.2283950617283955e-05,
37
+ "loss": 0.836,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "learning_rate": 3.9197530864197535e-05,
43
+ "loss": 0.7532,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.8875,
49
+ "eval_loss": 0.5960062742233276,
50
+ "eval_runtime": 0.9405,
51
+ "eval_samples_per_second": 255.183,
52
+ "eval_steps_per_second": 15.949,
53
+ "step": 60
54
+ }
55
+ ],
56
+ "max_steps": 180,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 8.71551101952e+16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-60/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed46c74c84ed7c649b9a6c9f49ebc80fd9e19c4d55f5e4b624542952595b972
3
+ size 4088
config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Sound_Guitar",
62
+ "1": "Sound_Drum",
63
+ "2": "Sound_Piano"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "label2id": {
68
+ "Sound_Drum": 1,
69
+ "Sound_Guitar": 0,
70
+ "Sound_Piano": 2
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.05,
80
+ "model_type": "wav2vec2",
81
+ "num_adapter_layers": 3,
82
+ "num_attention_heads": 12,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 12,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 768,
91
+ "pad_token_id": 0,
92
+ "proj_codevector_dim": 256,
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.28.1",
116
+ "use_weighted_layer_sum": false,
117
+ "vocab_size": 32,
118
+ "xvector_output_dim": 512
119
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84a5098ba7544003f7a1683d452bc3196d0f3d8a043afb34bd627a539fcdab4
3
+ size 378351910
runs/Jul12_22-57-29_bfd727bb6ba4/1752361052.536027/events.out.tfevents.1752361052.bfd727bb6ba4.23677.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30171822fce3bd18675626c9b458310f066c5596f49d7afd5f820c473717971
3
+ size 5933
runs/Jul12_22-57-29_bfd727bb6ba4/events.out.tfevents.1752361052.bfd727bb6ba4.23677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835e50cd5eb05e7836e6abd2a16cd1ef2dc5a0e2a6799dd7864a0f0da18259a9
3
+ size 9757
runs/Jul12_22-57-29_bfd727bb6ba4/events.out.tfevents.1752361168.bfd727bb6ba4.23677.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9fb431e37031e1417efe1c4fdce69321635e69a8e0a66f18a7decec6aae514
3
+ size 411
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed46c74c84ed7c649b9a6c9f49ebc80fd9e19c4d55f5e4b624542952595b972
3
+ size 4088