justin1983 commited on
Commit
111d425
1 Parent(s): 7030dfb

Training in progress, epoch 1

Browse files
.DS_Store CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0384ff887d7e47784154a5f1d2ecb574d8cd6e44455bc41708b7d809771e73a3
3
  size 6148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c28b9cfef41508af6fe4c668a74216cf157a52ec5b2dc5a416aebac58e6b3a
3
  size 6148
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./wav2vec2-base-finetuned-amd/checkpoint-392",
3
  "activation_dropout": 0.0,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
 
1
  {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
  "activation_dropout": 0.0,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
last-checkpoint/config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
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_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": "human",
60
+ "1": "machine",
61
+ "2": "not_sure"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "human": "0",
67
+ "machine": "1",
68
+ "not_sure": "2"
69
+ },
70
+ "layer_norm_eps": 1e-05,
71
+ "layerdrop": 0.0,
72
+ "mask_channel_length": 10,
73
+ "mask_channel_min_space": 1,
74
+ "mask_channel_other": 0.0,
75
+ "mask_channel_prob": 0.0,
76
+ "mask_channel_selection": "static",
77
+ "mask_feature_length": 10,
78
+ "mask_feature_min_masks": 0,
79
+ "mask_feature_prob": 0.0,
80
+ "mask_time_length": 10,
81
+ "mask_time_min_masks": 2,
82
+ "mask_time_min_space": 1,
83
+ "mask_time_other": 0.0,
84
+ "mask_time_prob": 0.05,
85
+ "mask_time_selection": "static",
86
+ "model_type": "wav2vec2",
87
+ "no_mask_channel_overlap": false,
88
+ "no_mask_time_overlap": false,
89
+ "num_adapter_layers": 3,
90
+ "num_attention_heads": 12,
91
+ "num_codevector_groups": 2,
92
+ "num_codevectors_per_group": 320,
93
+ "num_conv_pos_embedding_groups": 16,
94
+ "num_conv_pos_embeddings": 128,
95
+ "num_feat_extract_layers": 7,
96
+ "num_hidden_layers": 12,
97
+ "num_negatives": 100,
98
+ "output_hidden_size": 768,
99
+ "pad_token_id": 0,
100
+ "proj_codevector_dim": 256,
101
+ "tdnn_dilation": [
102
+ 1,
103
+ 2,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "tdnn_dim": [
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 512,
113
+ 1500
114
+ ],
115
+ "tdnn_kernel": [
116
+ 5,
117
+ 3,
118
+ 3,
119
+ 1,
120
+ 1
121
+ ],
122
+ "torch_dtype": "float32",
123
+ "transformers_version": "4.28.0",
124
+ "use_weighted_layer_sum": false,
125
+ "vocab_size": 32,
126
+ "xvector_output_dim": 512
127
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b0e0e36d4c1838fca71fdc7b94a6fd185942b075e8a48172876235e2360364e
3
+ size 756674757
last-checkpoint/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
+ }
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62371da9d1efb6c2ddfdbba1e3369bd3992b0b45a62ae0f90833ae9a0e67570
3
+ size 378348457
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc985cbff081d3144e1e3bd17099e393ba8f254a5d4a7b7c8a3bb769fd8f9119
3
+ size 13617
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909b58be1dc9ed7dc047b2a24dc032bcdc889b7dd37197f08921ab0c9dfa5ad9
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.844,
3
+ "best_model_checkpoint": "wav2vec2-base-finetuned-amd/checkpoint-204",
4
+ "epoch": 1.0,
5
+ "global_step": 204,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 4.877450980392157e-05,
13
+ "loss": 0.8606,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "learning_rate": 4.7549019607843135e-05,
19
+ "loss": 0.6482,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.15,
24
+ "learning_rate": 4.632352941176471e-05,
25
+ "loss": 0.5457,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.2,
30
+ "learning_rate": 4.5098039215686275e-05,
31
+ "loss": 0.5627,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.25,
36
+ "learning_rate": 4.387254901960784e-05,
37
+ "loss": 0.5341,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.29,
42
+ "learning_rate": 4.2647058823529415e-05,
43
+ "loss": 0.4305,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.34,
48
+ "learning_rate": 4.142156862745099e-05,
49
+ "loss": 0.4228,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.39,
54
+ "learning_rate": 4.0196078431372555e-05,
55
+ "loss": 0.4348,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.44,
60
+ "learning_rate": 3.897058823529412e-05,
61
+ "loss": 0.4506,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.49,
66
+ "learning_rate": 3.774509803921569e-05,
67
+ "loss": 0.4409,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.54,
72
+ "learning_rate": 3.6519607843137254e-05,
73
+ "loss": 0.3882,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.59,
78
+ "learning_rate": 3.529411764705883e-05,
79
+ "loss": 0.4034,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.64,
84
+ "learning_rate": 3.4068627450980394e-05,
85
+ "loss": 0.4629,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.69,
90
+ "learning_rate": 3.284313725490196e-05,
91
+ "loss": 0.4908,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.74,
96
+ "learning_rate": 3.161764705882353e-05,
97
+ "loss": 0.3667,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.78,
102
+ "learning_rate": 3.0392156862745097e-05,
103
+ "loss": 0.3918,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.83,
108
+ "learning_rate": 2.916666666666667e-05,
109
+ "loss": 0.3655,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.88,
114
+ "learning_rate": 2.7941176470588236e-05,
115
+ "loss": 0.4247,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.93,
120
+ "learning_rate": 2.6715686274509806e-05,
121
+ "loss": 0.3793,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.98,
126
+ "learning_rate": 2.5490196078431373e-05,
127
+ "loss": 0.368,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 1.0,
132
+ "eval_accuracy": 0.844,
133
+ "eval_loss": 0.27008941769599915,
134
+ "eval_runtime": 1114.9265,
135
+ "eval_samples_per_second": 4.933,
136
+ "eval_steps_per_second": 0.154,
137
+ "step": 204
138
+ }
139
+ ],
140
+ "max_steps": 408,
141
+ "num_train_epochs": 2,
142
+ "total_flos": 1.77769188826272e+17,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ce9497385c488a22ae92cb2249699d4cb97b3e82921cf19befde92665fa9b5
3
+ size 3643
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b1c17098e1ed373d149a01209285984e249be9ab882b64d43e5f92216bfedb1
3
  size 378348457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62371da9d1efb6c2ddfdbba1e3369bd3992b0b45a62ae0f90833ae9a0e67570
3
  size 378348457
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd60677461cd783192a5df1698c5c1cfb9c27de3a7ac928c78ec0f1614c3f2a8
3
  size 3643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ce9497385c488a22ae92cb2249699d4cb97b3e82921cf19befde92665fa9b5
3
  size 3643