Hugging Face's logo

arshsin
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
arshsin commited on
Commit
ae4249a
•
1 Parent(s): bdd3a55

Training in progress, epoch 3, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-85/config.json +96 -0
  2. checkpoint-85/model.safetensors +3 -0
  3. checkpoint-85/optimizer.pt +3 -0
  4. checkpoint-85/preprocessor_config.json +9 -0
  5. checkpoint-85/rng_state.pth +3 -0
  6. checkpoint-85/scheduler.pt +3 -0
  7. checkpoint-85/trainer_state.json +157 -0
  8. checkpoint-85/training_args.bin +3 -0
checkpoint-85/config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "arshsin/distilhubert-finetuned-gtzan",
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": "blues",
53
+ "1": "classical",
54
+ "2": "country",
55
+ "3": "disco",
56
+ "4": "hiphop",
57
+ "5": "jazz",
58
+ "6": "metal",
59
+ "7": "pop",
60
+ "8": "reggae",
61
+ "9": "rock"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "blues": "0",
67
+ "classical": "1",
68
+ "country": "2",
69
+ "disco": "3",
70
+ "hiphop": "4",
71
+ "jazz": "5",
72
+ "metal": "6",
73
+ "pop": "7",
74
+ "reggae": "8",
75
+ "rock": "9"
76
+ },
77
+ "layer_norm_eps": 1e-05,
78
+ "layerdrop": 0.0,
79
+ "mask_feature_length": 10,
80
+ "mask_feature_min_masks": 0,
81
+ "mask_feature_prob": 0.0,
82
+ "mask_time_length": 10,
83
+ "mask_time_min_masks": 2,
84
+ "mask_time_prob": 0.05,
85
+ "model_type": "hubert",
86
+ "num_attention_heads": 12,
87
+ "num_conv_pos_embedding_groups": 16,
88
+ "num_conv_pos_embeddings": 128,
89
+ "num_feat_extract_layers": 7,
90
+ "num_hidden_layers": 2,
91
+ "pad_token_id": 0,
92
+ "torch_dtype": "float32",
93
+ "transformers_version": "4.35.2",
94
+ "use_weighted_layer_sum": false,
95
+ "vocab_size": 32
96
+ }
checkpoint-85/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29ea7d54fd5609806bbc21054a0eaf918036aa5c0ccd4a443ffde67e9d14cd7
3
+ size 94771728
checkpoint-85/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87a1f48455e9686edd20058e024cb7e770af8462cabab13c546c967f9c8b6be
3
+ size 189575930
checkpoint-85/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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-85/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b90b6951c86e6523341aa86e4425c6ebd2487d6a65c88806ecd949cf1a18b6
3
+ size 14244
checkpoint-85/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b22bd3f3c41599ff5eaa7e33debfdeaff053883961fa7206cb1c77b15ba5140
3
+ size 1064
checkpoint-85/trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.85,
3
+ "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-64",
4
+ "epoch": 3.966666666666667,
5
+ "eval_steps": 500,
6
+ "global_step": 85,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 9.523809523809525e-06,
14
+ "loss": 0.0321,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.904761904761905e-05,
20
+ "loss": 0.0077,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 2.8571428571428574e-05,
26
+ "loss": 0.0345,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.93,
31
+ "learning_rate": 3.80952380952381e-05,
32
+ "loss": 0.0009,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.98,
37
+ "eval_accuracy": 0.84,
38
+ "eval_loss": 1.215333342552185,
39
+ "eval_runtime": 71.621,
40
+ "eval_samples_per_second": 1.396,
41
+ "eval_steps_per_second": 0.237,
42
+ "step": 21
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 3.9153439153439155e-05,
47
+ "loss": 0.0094,
48
+ "step": 25
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 3.80952380952381e-05,
53
+ "loss": 0.0319,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 1.63,
58
+ "learning_rate": 3.703703703703704e-05,
59
+ "loss": 0.0006,
60
+ "step": 35
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 3.597883597883598e-05,
65
+ "loss": 0.0122,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 1.96,
70
+ "eval_accuracy": 0.82,
71
+ "eval_loss": 1.2078099250793457,
72
+ "eval_runtime": 72.4494,
73
+ "eval_samples_per_second": 1.38,
74
+ "eval_steps_per_second": 0.235,
75
+ "step": 42
76
+ },
77
+ {
78
+ "epoch": 2.1,
79
+ "learning_rate": 3.4920634920634925e-05,
80
+ "loss": 0.0043,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 2.33,
85
+ "learning_rate": 3.386243386243386e-05,
86
+ "loss": 0.0004,
87
+ "step": 50
88
+ },
89
+ {
90
+ "epoch": 2.57,
91
+ "learning_rate": 3.280423280423281e-05,
92
+ "loss": 0.0003,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 2.8,
97
+ "learning_rate": 3.1746031746031745e-05,
98
+ "loss": 0.0204,
99
+ "step": 60
100
+ },
101
+ {
102
+ "epoch": 2.99,
103
+ "eval_accuracy": 0.85,
104
+ "eval_loss": 1.3243606090545654,
105
+ "eval_runtime": 72.2701,
106
+ "eval_samples_per_second": 1.384,
107
+ "eval_steps_per_second": 0.235,
108
+ "step": 64
109
+ },
110
+ {
111
+ "epoch": 3.03,
112
+ "learning_rate": 3.068783068783069e-05,
113
+ "loss": 0.0384,
114
+ "step": 65
115
+ },
116
+ {
117
+ "epoch": 3.27,
118
+ "learning_rate": 2.962962962962963e-05,
119
+ "loss": 0.0003,
120
+ "step": 70
121
+ },
122
+ {
123
+ "epoch": 3.5,
124
+ "learning_rate": 2.8571428571428574e-05,
125
+ "loss": 0.0002,
126
+ "step": 75
127
+ },
128
+ {
129
+ "epoch": 3.73,
130
+ "learning_rate": 2.7513227513227515e-05,
131
+ "loss": 0.0381,
132
+ "step": 80
133
+ },
134
+ {
135
+ "epoch": 3.97,
136
+ "learning_rate": 2.645502645502646e-05,
137
+ "loss": 0.0163,
138
+ "step": 85
139
+ },
140
+ {
141
+ "epoch": 3.97,
142
+ "eval_accuracy": 0.84,
143
+ "eval_loss": 1.3357460498809814,
144
+ "eval_runtime": 72.1033,
145
+ "eval_samples_per_second": 1.387,
146
+ "eval_steps_per_second": 0.236,
147
+ "step": 85
148
+ }
149
+ ],
150
+ "logging_steps": 5,
151
+ "max_steps": 210,
152
+ "num_train_epochs": 10,
153
+ "save_steps": 500,
154
+ "total_flos": 2.4535953098496e+17,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }
checkpoint-85/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993ac23386c550d4dd26922cb1cbafc1a8195ab1902207d39addd6b52e321d14
3
+ size 4600