Hugging Face's logo

ameerazam08
/
Hubert-Speech-Fluency

Transformers
PyTorch
TensorBoard
hubert
Inference Endpoints
Model card Files Metrics Community
ameerazam08 commited on
Commit
3b11f8a
•
1 Parent(s): 9339f13

Done Hubert

Browse files
Files changed (15) hide show
  1. all_results.json +9 -0
  2. config.json +89 -0
  3. optimizer.pt +3 -0
  4. preprocessor_config.json +9 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. runs/Sep21_11-36-21_gpu-vision-2/1663760201.520889/events.out.tfevents.1663760201.gpu-vision-2.441101.1 +3 -0
  8. runs/Sep21_11-36-21_gpu-vision-2/1663760271.2318697/events.out.tfevents.1663760271.gpu-vision-2.441101.3 +3 -0
  9. runs/Sep21_11-36-21_gpu-vision-2/events.out.tfevents.1663760201.gpu-vision-2.441101.0 +3 -0
  10. runs/Sep21_11-36-21_gpu-vision-2/events.out.tfevents.1663760271.gpu-vision-2.441101.2 +3 -0
  11. scaler.pt +3 -0
  12. scheduler.pt +3 -0
  13. train_results.json +9 -0
  14. trainer_state.json +106 -0
  15. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 6.56395391232e+16,
4
+ "train_loss": 0.8879674275716146,
5
+ "train_runtime": 149.0278,
6
+ "train_samples": 480,
7
+ "train_samples_per_second": 3.221,
8
+ "train_steps_per_second": 0.403
9
+ }
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/hubert-base-ls960",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "HubertForSpeechClassification"
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_dropout": 0.0,
45
+ "feat_extract_norm": "group",
46
+ "feat_proj_dropout": 0.1,
47
+ "feat_proj_layer_norm": true,
48
+ "final_dropout": 0.1,
49
+ "finetuning_task": "wav2vec2_clf",
50
+ "gradient_checkpointing": false,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_dropout_prob": 0.1,
54
+ "hidden_size": 768,
55
+ "id2label": {
56
+ "0": "High",
57
+ "1": "Intermediate",
58
+ "2": "Low"
59
+ },
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "High": 0,
64
+ "Intermediate": 1,
65
+ "Low": 2
66
+ },
67
+ "layer_norm_eps": 1e-05,
68
+ "layerdrop": 0.1,
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_prob": 0.05,
75
+ "model_type": "hubert",
76
+ "num_attention_heads": 12,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 128,
79
+ "num_feat_extract_layers": 7,
80
+ "num_hidden_layers": 12,
81
+ "pad_token_id": 0,
82
+ "pooling_mode": "mean",
83
+ "problem_type": "single_label_classification",
84
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.23.0.dev0",
87
+ "use_weighted_layer_sum": false,
88
+ "vocab_size": 32
89
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d960f4a7d68c774df99ca9fbd3e8d2ae46bba01c1eed359eabb814b3c2b77ecc
3
+ size 726232521
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": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0849484c362555ff06c7ab4faa7c01e999512921e7a1fa7714f2a80983da3bdc
3
+ size 379930259
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee888d44dfec4f927b98490c9522a6ffd0f5cbb8dddd287cb0ca70eefc52be1d
3
+ size 14567
runs/Sep21_11-36-21_gpu-vision-2/1663760201.520889/events.out.tfevents.1663760201.gpu-vision-2.441101.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42d7960b71335b6dd179186ed6a949ef7b2025a79bb12a4c0837e5c88f40978
3
+ size 5565
runs/Sep21_11-36-21_gpu-vision-2/1663760271.2318697/events.out.tfevents.1663760271.gpu-vision-2.441101.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6048fc95b74070b3cb0c276f0b85df30aa1f2ebfb8f2e81c9a7b57a9f37df69a
3
+ size 5565
runs/Sep21_11-36-21_gpu-vision-2/events.out.tfevents.1663760201.gpu-vision-2.441101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93bf7f53f71eb432a339384306e05635a0b2125070e934ce0c33f9dd425756c
3
+ size 4866
runs/Sep21_11-36-21_gpu-vision-2/events.out.tfevents.1663760271.gpu-vision-2.441101.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d92d6f31994e9adece86c0c41a8b0435ddb4bc84e35a548f6dbe8f19bb34799
3
+ size 8040
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e26ec2eeed5d2393eae8db5740c3d49711ae46ff10dcff4c5d8a4a07cdc5062
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce80575079d23ca9848485ebe4b4307b930e4e6837dbf65c0ee7b180d84498e
3
+ size 623
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 6.56395391232e+16,
4
+ "train_loss": 0.8879674275716146,
5
+ "train_runtime": 149.0278,
6
+ "train_samples": 480,
7
+ "train_samples_per_second": 3.221,
8
+ "train_steps_per_second": 0.403
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 60,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 8.333333333333334e-05,
13
+ "loss": 1.0298,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.17,
18
+ "eval_accuracy": 0.3583333194255829,
19
+ "eval_loss": 1.027502417564392,
20
+ "eval_runtime": 13.2982,
21
+ "eval_samples_per_second": 9.024,
22
+ "eval_steps_per_second": 2.256,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.33,
27
+ "learning_rate": 6.666666666666667e-05,
28
+ "loss": 0.9216,
29
+ "step": 20
30
+ },
31
+ {
32
+ "epoch": 0.33,
33
+ "eval_accuracy": 0.6583333611488342,
34
+ "eval_loss": 0.9037414789199829,
35
+ "eval_runtime": 13.3332,
36
+ "eval_samples_per_second": 9.0,
37
+ "eval_steps_per_second": 2.25,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.5,
42
+ "learning_rate": 5e-05,
43
+ "loss": 0.9802,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.5,
48
+ "eval_accuracy": 0.34166666865348816,
49
+ "eval_loss": 0.9806223511695862,
50
+ "eval_runtime": 13.2424,
51
+ "eval_samples_per_second": 9.062,
52
+ "eval_steps_per_second": 2.265,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 0.67,
57
+ "learning_rate": 3.3333333333333335e-05,
58
+ "loss": 0.8864,
59
+ "step": 40
60
+ },
61
+ {
62
+ "epoch": 0.67,
63
+ "eval_accuracy": 0.699999988079071,
64
+ "eval_loss": 0.8415695428848267,
65
+ "eval_runtime": 13.0866,
66
+ "eval_samples_per_second": 9.17,
67
+ "eval_steps_per_second": 2.292,
68
+ "step": 40
69
+ },
70
+ {
71
+ "epoch": 0.83,
72
+ "learning_rate": 1.6666666666666667e-05,
73
+ "loss": 0.753,
74
+ "step": 50
75
+ },
76
+ {
77
+ "epoch": 0.83,
78
+ "eval_accuracy": 0.7083333134651184,
79
+ "eval_loss": 0.7226903438568115,
80
+ "eval_runtime": 13.037,
81
+ "eval_samples_per_second": 9.205,
82
+ "eval_steps_per_second": 2.301,
83
+ "step": 50
84
+ },
85
+ {
86
+ "epoch": 1.0,
87
+ "learning_rate": 0.0,
88
+ "loss": 0.7567,
89
+ "step": 60
90
+ },
91
+ {
92
+ "epoch": 1.0,
93
+ "eval_accuracy": 0.7083333134651184,
94
+ "eval_loss": 0.7225412726402283,
95
+ "eval_runtime": 13.0892,
96
+ "eval_samples_per_second": 9.168,
97
+ "eval_steps_per_second": 2.292,
98
+ "step": 60
99
+ }
100
+ ],
101
+ "max_steps": 60,
102
+ "num_train_epochs": 1,
103
+ "total_flos": 6.56395391232e+16,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826d2fb73a8c1fde81ac603dd39b2df510815f6a3150f35c8c114b4b9b119ccd
3
+ size 3439