Hugging Face's logo

anderloh
/
FineTunedModel

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Model card Files
xet
Metrics Community
1
anderloh commited on
Commit
5871bd1
·
1 Parent(s): a358cec

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +126 -0
  2. optimizer.pt +3 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +169 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "children_playing",
61
+ "1": "dog_bark"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "children_playing": "0",
67
+ "dog_bark": "1"
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "layerdrop": 0.0,
71
+ "mask_channel_length": 10,
72
+ "mask_channel_min_space": 1,
73
+ "mask_channel_other": 0.0,
74
+ "mask_channel_prob": 0.0,
75
+ "mask_channel_selection": "static",
76
+ "mask_feature_length": 10,
77
+ "mask_feature_min_masks": 0,
78
+ "mask_feature_prob": 0.0,
79
+ "mask_time_length": 10,
80
+ "mask_time_min_masks": 2,
81
+ "mask_time_min_space": 1,
82
+ "mask_time_other": 0.0,
83
+ "mask_time_prob": 0.05,
84
+ "mask_time_selection": "static",
85
+ "model_type": "wav2vec2",
86
+ "no_mask_channel_overlap": false,
87
+ "no_mask_time_overlap": false,
88
+ "num_adapter_layers": 3,
89
+ "num_attention_heads": 12,
90
+ "num_codevector_groups": 2,
91
+ "num_codevectors_per_group": 320,
92
+ "num_conv_pos_embedding_groups": 16,
93
+ "num_conv_pos_embeddings": 128,
94
+ "num_feat_extract_layers": 7,
95
+ "num_hidden_layers": 12,
96
+ "num_negatives": 100,
97
+ "output_hidden_size": 768,
98
+ "pad_token_id": 0,
99
+ "proj_codevector_dim": 256,
100
+ "tdnn_dilation": [
101
+ 1,
102
+ 2,
103
+ 3,
104
+ 1,
105
+ 1
106
+ ],
107
+ "tdnn_dim": [
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 1500
113
+ ],
114
+ "tdnn_kernel": [
115
+ 5,
116
+ 3,
117
+ 3,
118
+ 1,
119
+ 1
120
+ ],
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.34.1",
123
+ "use_weighted_layer_sum": false,
124
+ "vocab_size": 32,
125
+ "xvector_output_dim": 512
126
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab1aca21d4f21e60c4bb589b4f4da1060ef193a159e05478d04902cce624082
3
+ size 756677285
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b27857ec024b7350ac1c9b776cd909d00a270704529bd4a137b2bb8d6c4229
3
+ size 378348563
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b32a6bdd9dedc7a2e436458fa769f9f9cd42b07e97fec6f951653cd8b8de8f2
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f7973da5c7a8dc8410f3216c09f4648fa73119a2620fc25ea18a5fa2d41399
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "finetuned\\checkpoint-5",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
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
+ "learning_rate": 5e-05,
14
+ "loss": 0.7055,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 1.0,
20
+ "eval_loss": 0.6571568846702576,
21
+ "eval_runtime": 0.0813,
22
+ "eval_samples_per_second": 24.587,
23
+ "eval_steps_per_second": 12.294,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 4.4444444444444447e-05,
29
+ "loss": 0.667,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.0,
35
+ "eval_loss": 0.9093643426895142,
36
+ "eval_runtime": 0.0391,
37
+ "eval_samples_per_second": 51.099,
38
+ "eval_steps_per_second": 25.549,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.888888888888889e-05,
44
+ "loss": 0.6129,
45
+ "step": 15
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 1.0,
50
+ "eval_loss": 0.6191004514694214,
51
+ "eval_runtime": 0.0397,
52
+ "eval_samples_per_second": 50.333,
53
+ "eval_steps_per_second": 25.167,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 3.3333333333333335e-05,
59
+ "loss": 0.6345,
60
+ "step": 20
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.5,
65
+ "eval_loss": 0.6391083002090454,
66
+ "eval_runtime": 0.0399,
67
+ "eval_samples_per_second": 50.142,
68
+ "eval_steps_per_second": 25.071,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 2.777777777777778e-05,
74
+ "loss": 0.5029,
75
+ "step": 25
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.5,
80
+ "eval_loss": 0.6429222822189331,
81
+ "eval_runtime": 0.0473,
82
+ "eval_samples_per_second": 42.326,
83
+ "eval_steps_per_second": 21.163,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 2.2222222222222223e-05,
89
+ "loss": 0.4698,
90
+ "step": 30
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.5,
95
+ "eval_loss": 0.6175457239151001,
96
+ "eval_runtime": 0.0518,
97
+ "eval_samples_per_second": 38.587,
98
+ "eval_steps_per_second": 19.294,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 1.6666666666666667e-05,
104
+ "loss": 0.3119,
105
+ "step": 35
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 1.0,
110
+ "eval_loss": 0.43689876794815063,
111
+ "eval_runtime": 0.041,
112
+ "eval_samples_per_second": 48.823,
113
+ "eval_steps_per_second": 24.411,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 1.1111111111111112e-05,
119
+ "loss": 0.286,
120
+ "step": 40
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.5,
125
+ "eval_loss": 0.7379075884819031,
126
+ "eval_runtime": 0.0397,
127
+ "eval_samples_per_second": 50.369,
128
+ "eval_steps_per_second": 25.185,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "learning_rate": 5.555555555555556e-06,
134
+ "loss": 0.2241,
135
+ "step": 45
136
+ },
137
+ {
138
+ "epoch": 9.0,
139
+ "eval_accuracy": 0.5,
140
+ "eval_loss": 0.8524875044822693,
141
+ "eval_runtime": 0.0431,
142
+ "eval_samples_per_second": 46.432,
143
+ "eval_steps_per_second": 23.216,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 10.0,
148
+ "learning_rate": 0.0,
149
+ "loss": 0.1981,
150
+ "step": 50
151
+ },
152
+ {
153
+ "epoch": 10.0,
154
+ "eval_accuracy": 0.5,
155
+ "eval_loss": 0.8950199484825134,
156
+ "eval_runtime": 0.0399,
157
+ "eval_samples_per_second": 50.108,
158
+ "eval_steps_per_second": 25.054,
159
+ "step": 50
160
+ }
161
+ ],
162
+ "logging_steps": 5,
163
+ "max_steps": 50,
164
+ "num_train_epochs": 10,
165
+ "save_steps": 500,
166
+ "total_flos": 1539644174588520.0,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9d1df1472fc9f8c3ab59c9507586079994ea1a1d3b1ce6794c21f80060fa80
3
+ size 4015