Hugging Face's logo

Erik3Zg
/
MTL-Distilhubert-Marimba

Audio Classification
Transformers
Safetensors
hubert
Model card Files
xet
 Community
Erik3Zg commited on
Commit
53534c4
·
verified ·
1 Parent(s): 53dfa6d

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +116 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. preprocessor_config.json +9 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +145 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 768,
51
+ "id2label": {
52
+ "0": "LABEL_0",
53
+ "1": "LABEL_1",
54
+ "2": "LABEL_2",
55
+ "3": "LABEL_3",
56
+ "4": "LABEL_4",
57
+ "5": "LABEL_5",
58
+ "6": "LABEL_6",
59
+ "7": "LABEL_7",
60
+ "8": "LABEL_8",
61
+ "9": "LABEL_9",
62
+ "10": "LABEL_10",
63
+ "11": "LABEL_11",
64
+ "12": "LABEL_12",
65
+ "13": "LABEL_13",
66
+ "14": "LABEL_14",
67
+ "15": "LABEL_15",
68
+ "16": "LABEL_16",
69
+ "17": "LABEL_17",
70
+ "18": "LABEL_18",
71
+ "19": "LABEL_19"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "LABEL_0": 0,
77
+ "LABEL_1": 1,
78
+ "LABEL_10": 10,
79
+ "LABEL_11": 11,
80
+ "LABEL_12": 12,
81
+ "LABEL_13": 13,
82
+ "LABEL_14": 14,
83
+ "LABEL_15": 15,
84
+ "LABEL_16": 16,
85
+ "LABEL_17": 17,
86
+ "LABEL_18": 18,
87
+ "LABEL_19": 19,
88
+ "LABEL_2": 2,
89
+ "LABEL_3": 3,
90
+ "LABEL_4": 4,
91
+ "LABEL_5": 5,
92
+ "LABEL_6": 6,
93
+ "LABEL_7": 7,
94
+ "LABEL_8": 8,
95
+ "LABEL_9": 9
96
+ },
97
+ "layer_norm_eps": 1e-05,
98
+ "layerdrop": 0.0,
99
+ "mask_feature_length": 10,
100
+ "mask_feature_min_masks": 0,
101
+ "mask_feature_prob": 0.0,
102
+ "mask_time_length": 10,
103
+ "mask_time_min_masks": 2,
104
+ "mask_time_prob": 0.05,
105
+ "model_type": "hubert",
106
+ "num_attention_heads": 12,
107
+ "num_conv_pos_embedding_groups": 16,
108
+ "num_conv_pos_embeddings": 128,
109
+ "num_feat_extract_layers": 7,
110
+ "num_hidden_layers": 2,
111
+ "pad_token_id": 0,
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.39.3",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 32
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4ed21023df5f79c9bf00996eb8b05d9ff63914c931a04a4777b0d85ecb730e
3
+ size 94782008
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc79c4003f6af91964c5c68364c6df6e4d9e9241936184f8cd995798783dd17
3
+ size 189596538
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
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664b1196f110f17c5ab8686d1a3e6ea9367dcbace9a63b16b6b42bdfe0892846
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56251b046e7a9d0ca44cd9a61d2356bc2bfc323d763eb05420cc0c6f1e732d28
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8488888888888889,
3
+ "best_model_checkpoint": "MTL-Distilhubert-Marimba/checkpoint-1130",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.25333333333333335,
14
+ "eval_loss": 2.2405927181243896,
15
+ "eval_precision": 0.12995506339271384,
16
+ "eval_recall": 0.25333333333333335,
17
+ "eval_runtime": 314.4075,
18
+ "eval_samples_per_second": 2.863,
19
+ "eval_steps_per_second": 0.359,
20
+ "step": 113
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.3688888888888889,
25
+ "eval_loss": 1.8393090963363647,
26
+ "eval_precision": 0.2575408636868126,
27
+ "eval_recall": 0.3688888888888889,
28
+ "eval_runtime": 315.177,
29
+ "eval_samples_per_second": 2.856,
30
+ "eval_steps_per_second": 0.359,
31
+ "step": 226
32
+ },
33
+ {
34
+ "epoch": 3.0,
35
+ "eval_accuracy": 0.4711111111111111,
36
+ "eval_loss": 1.560020923614502,
37
+ "eval_precision": 0.4683247159340995,
38
+ "eval_recall": 0.4711111111111111,
39
+ "eval_runtime": 313.1058,
40
+ "eval_samples_per_second": 2.874,
41
+ "eval_steps_per_second": 0.361,
42
+ "step": 339
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_accuracy": 0.5433333333333333,
47
+ "eval_loss": 1.335411548614502,
48
+ "eval_precision": 0.5248222638705001,
49
+ "eval_recall": 0.5433333333333333,
50
+ "eval_runtime": 313.2962,
51
+ "eval_samples_per_second": 2.873,
52
+ "eval_steps_per_second": 0.361,
53
+ "step": 452
54
+ },
55
+ {
56
+ "epoch": 4.42,
57
+ "grad_norm": 3801843.0,
58
+ "learning_rate": 3.097345132743363e-05,
59
+ "loss": 1.9322,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "eval_accuracy": 0.6288888888888889,
65
+ "eval_loss": 1.14306640625,
66
+ "eval_precision": 0.5920881604772438,
67
+ "eval_recall": 0.6288888888888889,
68
+ "eval_runtime": 312.8717,
69
+ "eval_samples_per_second": 2.877,
70
+ "eval_steps_per_second": 0.361,
71
+ "step": 565
72
+ },
73
+ {
74
+ "epoch": 6.0,
75
+ "eval_accuracy": 0.7055555555555556,
76
+ "eval_loss": 1.0195263624191284,
77
+ "eval_precision": 0.7640782034160968,
78
+ "eval_recall": 0.7055555555555556,
79
+ "eval_runtime": 312.7157,
80
+ "eval_samples_per_second": 2.878,
81
+ "eval_steps_per_second": 0.361,
82
+ "step": 678
83
+ },
84
+ {
85
+ "epoch": 7.0,
86
+ "eval_accuracy": 0.7344444444444445,
87
+ "eval_loss": 0.8860337734222412,
88
+ "eval_precision": 0.7796715530584135,
89
+ "eval_recall": 0.7344444444444445,
90
+ "eval_runtime": 311.6307,
91
+ "eval_samples_per_second": 2.888,
92
+ "eval_steps_per_second": 0.363,
93
+ "step": 791
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.8066666666666666,
98
+ "eval_loss": 0.7833626866340637,
99
+ "eval_precision": 0.819842570108008,
100
+ "eval_recall": 0.8066666666666666,
101
+ "eval_runtime": 311.3217,
102
+ "eval_samples_per_second": 2.891,
103
+ "eval_steps_per_second": 0.363,
104
+ "step": 904
105
+ },
106
+ {
107
+ "epoch": 8.85,
108
+ "grad_norm": 3098557.75,
109
+ "learning_rate": 6.3913470993117005e-06,
110
+ "loss": 1.0332,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 9.0,
115
+ "eval_accuracy": 0.8477777777777777,
116
+ "eval_loss": 0.7198149561882019,
117
+ "eval_precision": 0.8561166941855263,
118
+ "eval_recall": 0.8477777777777777,
119
+ "eval_runtime": 311.0374,
120
+ "eval_samples_per_second": 2.894,
121
+ "eval_steps_per_second": 0.363,
122
+ "step": 1017
123
+ },
124
+ {
125
+ "epoch": 10.0,
126
+ "eval_accuracy": 0.8488888888888889,
127
+ "eval_loss": 0.7008057236671448,
128
+ "eval_precision": 0.8574701217585612,
129
+ "eval_recall": 0.8488888888888889,
130
+ "eval_runtime": 311.2934,
131
+ "eval_samples_per_second": 2.891,
132
+ "eval_steps_per_second": 0.363,
133
+ "step": 1130
134
+ }
135
+ ],
136
+ "logging_steps": 500,
137
+ "max_steps": 1130,
138
+ "num_input_tokens_seen": 0,
139
+ "num_train_epochs": 10,
140
+ "save_steps": 500,
141
+ "total_flos": 3.0707387712e+17,
142
+ "train_batch_size": 8,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9224401dbd46bc10ea90f37d83aab97aaf07d429103c938febeb50cb60bd552
3
+ size 4920