vadhri commited on
Commit
f8ad821
1 Parent(s): d009d3e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ model-index:
9
+ - name: music-genre-classifer-20-finetuned-gtzan
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # music-genre-classifer-20-finetuned-gtzan
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - eval_loss: 0.8423
21
+ - eval_accuracy: 0.79
22
+ - eval_runtime: 61.8646
23
+ - eval_samples_per_second: 1.616
24
+ - eval_steps_per_second: 0.21
25
+ - epoch: 9.0
26
+ - step: 1017
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 2e-05
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 10
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.38.2
58
+ - Pytorch 2.2.1+cu121
59
+ - Datasets 2.18.0
60
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eacc3e219d2379c01ca3317d7357517c25777c4947eea17213e7c0e8de52b8ae
3
  size 378310592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd713b3d6b7c78f55456ef775af0b24d69945154af587a39fecbb54347b38d59
3
  size 378310592
runs/Apr16_16-04-33_5164e8fbd75f/events.out.tfevents.1713283480.5164e8fbd75f.755.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15a20052603790f46da0e6f9f0c18402981949bfc75188ab60b245954ab87628
3
- size 42286
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86bbb942226473047ead36149463d683b81a942a20a462ea0a974713a413490a
3
+ size 52427
tmp-checkpoint-1017/config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "blues",
61
+ "1": "classical",
62
+ "2": "country",
63
+ "3": "disco",
64
+ "4": "hiphop",
65
+ "5": "jazz",
66
+ "6": "metal",
67
+ "7": "pop",
68
+ "8": "reggae",
69
+ "9": "rock"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "blues": "0",
75
+ "classical": "1",
76
+ "country": "2",
77
+ "disco": "3",
78
+ "hiphop": "4",
79
+ "jazz": "5",
80
+ "metal": "6",
81
+ "pop": "7",
82
+ "reggae": "8",
83
+ "rock": "9"
84
+ },
85
+ "layer_norm_eps": 1e-05,
86
+ "layerdrop": 0.0,
87
+ "mask_channel_length": 10,
88
+ "mask_channel_min_space": 1,
89
+ "mask_channel_other": 0.0,
90
+ "mask_channel_prob": 0.0,
91
+ "mask_channel_selection": "static",
92
+ "mask_feature_length": 10,
93
+ "mask_feature_min_masks": 0,
94
+ "mask_feature_prob": 0.0,
95
+ "mask_time_length": 10,
96
+ "mask_time_min_masks": 2,
97
+ "mask_time_min_space": 1,
98
+ "mask_time_other": 0.0,
99
+ "mask_time_prob": 0.05,
100
+ "mask_time_selection": "static",
101
+ "model_type": "wav2vec2",
102
+ "no_mask_channel_overlap": false,
103
+ "no_mask_time_overlap": false,
104
+ "num_adapter_layers": 3,
105
+ "num_attention_heads": 12,
106
+ "num_codevector_groups": 2,
107
+ "num_codevectors_per_group": 320,
108
+ "num_conv_pos_embedding_groups": 16,
109
+ "num_conv_pos_embeddings": 128,
110
+ "num_feat_extract_layers": 7,
111
+ "num_hidden_layers": 12,
112
+ "num_negatives": 100,
113
+ "output_hidden_size": 768,
114
+ "pad_token_id": 0,
115
+ "proj_codevector_dim": 256,
116
+ "tdnn_dilation": [
117
+ 1,
118
+ 2,
119
+ 3,
120
+ 1,
121
+ 1
122
+ ],
123
+ "tdnn_dim": [
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 512,
128
+ 1500
129
+ ],
130
+ "tdnn_kernel": [
131
+ 5,
132
+ 3,
133
+ 3,
134
+ 1,
135
+ 1
136
+ ],
137
+ "torch_dtype": "float32",
138
+ "transformers_version": "4.38.2",
139
+ "use_weighted_layer_sum": false,
140
+ "vocab_size": 32,
141
+ "xvector_output_dim": 512
142
+ }
tmp-checkpoint-1017/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd713b3d6b7c78f55456ef775af0b24d69945154af587a39fecbb54347b38d59
3
+ size 378310592
tmp-checkpoint-1017/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca31a44779aaf59a28b0550fbb87a7619e971b05bd2567c5fb4488a2843b321
3
+ size 468280468
tmp-checkpoint-1017/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": true,
8
+ "sampling_rate": 16000
9
+ }
tmp-checkpoint-1017/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1a654defe7e0ed61faffa7e65616d0cdddaaec1c42404e9df738a8ae9573ec
3
+ size 4984