marinone94 commited on
Commit
437dc11
1 Parent(s): 060c28e

remove checkpoints from repo

Browse files
.gitignore CHANGED
@@ -1,2 +1,3 @@
1
  *venv
2
- .ipynb_checkpoints/
 
 
1
  *venv
2
+ .ipynb_checkpoints/
3
+ checkpoint*/
checkpoint-1000/config.json DELETED
@@ -1,107 +0,0 @@
1
- {
2
- "_name_or_path": "marinone94/xls-r-300m-sv-robust",
3
- "activation_dropout": 0.1,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
- "apply_spec_augment": true,
8
- "architectures": [
9
- "Wav2Vec2ForCTC"
10
- ],
11
- "attention_dropout": 0.0,
12
- "bos_token_id": 1,
13
- "classifier_proj_size": 256,
14
- "codevector_dim": 768,
15
- "contrastive_logits_temperature": 0.1,
16
- "conv_bias": true,
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": "mean",
45
- "ctc_zero_infinity": false,
46
- "diversity_loss_weight": 0.1,
47
- "do_stable_layer_norm": true,
48
- "eos_token_id": 2,
49
- "feat_extract_activation": "gelu",
50
- "feat_extract_dropout": 0.0,
51
- "feat_extract_norm": "layer",
52
- "feat_proj_dropout": 0.0,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "hidden_act": "gelu",
56
- "hidden_dropout": 0.0,
57
- "hidden_size": 1024,
58
- "initializer_range": 0.02,
59
- "intermediate_size": 4096,
60
- "layer_norm_eps": 1e-05,
61
- "layerdrop": 0.0,
62
- "mask_feature_length": 64,
63
- "mask_feature_min_masks": 0,
64
- "mask_feature_prob": 0.25,
65
- "mask_time_length": 10,
66
- "mask_time_min_masks": 2,
67
- "mask_time_prob": 0.75,
68
- "model_type": "wav2vec2",
69
- "num_adapter_layers": 3,
70
- "num_attention_heads": 16,
71
- "num_codevector_groups": 2,
72
- "num_codevectors_per_group": 320,
73
- "num_conv_pos_embedding_groups": 16,
74
- "num_conv_pos_embeddings": 128,
75
- "num_feat_extract_layers": 7,
76
- "num_hidden_layers": 24,
77
- "num_negatives": 100,
78
- "output_hidden_size": 1024,
79
- "pad_token_id": 34,
80
- "proj_codevector_dim": 768,
81
- "tdnn_dilation": [
82
- 1,
83
- 2,
84
- 3,
85
- 1,
86
- 1
87
- ],
88
- "tdnn_dim": [
89
- 512,
90
- 512,
91
- 512,
92
- 512,
93
- 1500
94
- ],
95
- "tdnn_kernel": [
96
- 5,
97
- 3,
98
- 3,
99
- 1,
100
- 1
101
- ],
102
- "torch_dtype": "float32",
103
- "transformers_version": "4.16.0.dev0",
104
- "use_weighted_layer_sum": false,
105
- "vocab_size": 37,
106
- "xvector_output_dim": 512
107
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:997e39e3068f6334cf85b372c45d1b1aec7a201fbe1f730152e5d4a0b55fe960
3
- size 2490362385
 
 
 
 
checkpoint-1000/preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a0d1201f69f8dc32ebd7a780daea905f15db2bbd2da823ebd02ed30aa3bee71
3
- size 1262075377
 
 
 
 
checkpoint-1000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a3789e7a321dae6b4bf60417d43627b247a6090022ececb8fe9e7931554f2a6
3
- size 14503
 
 
 
 
checkpoint-1000/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:637182a715f3446bd8163c96f6b2a5376a6865fe60d3b7086f55025f5f89924a
3
- size 559
 
 
 
 
checkpoint-1000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a14af155fdce6ec463b3e3ef0c4d974d177934cf33badd4dcae71e1061f0d5
3
- size 623
 
 
 
 
checkpoint-1000/trainer_state.json DELETED
@@ -1,94 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.9050036258158087,
5
- "global_step": 1000,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.29,
12
- "learning_rate": 3.675e-06,
13
- "loss": 1.0197,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 0.58,
18
- "learning_rate": 7.425e-06,
19
- "loss": 1.0171,
20
- "step": 200
21
- },
22
- {
23
- "epoch": 0.87,
24
- "learning_rate": 1.1137499999999998e-05,
25
- "loss": 1.026,
26
- "step": 300
27
- },
28
- {
29
- "epoch": 1.16,
30
- "learning_rate": 1.48875e-05,
31
- "loss": 1.0383,
32
- "step": 400
33
- },
34
- {
35
- "epoch": 1.45,
36
- "learning_rate": 1.86375e-05,
37
- "loss": 1.0296,
38
- "step": 500
39
- },
40
- {
41
- "epoch": 1.45,
42
- "eval_loss": 0.3191435635089874,
43
- "eval_runtime": 138.7872,
44
- "eval_samples_per_second": 33.288,
45
- "eval_steps_per_second": 4.165,
46
- "eval_wer": 0.27421526035611576,
47
- "step": 500
48
- },
49
- {
50
- "epoch": 1.74,
51
- "learning_rate": 2.23875e-05,
52
- "loss": 1.0529,
53
- "step": 600
54
- },
55
- {
56
- "epoch": 2.03,
57
- "learning_rate": 2.6137499999999995e-05,
58
- "loss": 1.0442,
59
- "step": 700
60
- },
61
- {
62
- "epoch": 2.32,
63
- "learning_rate": 2.9887499999999998e-05,
64
- "loss": 1.0632,
65
- "step": 800
66
- },
67
- {
68
- "epoch": 2.61,
69
- "learning_rate": 3.36375e-05,
70
- "loss": 1.037,
71
- "step": 900
72
- },
73
- {
74
- "epoch": 2.91,
75
- "learning_rate": 3.7387499999999994e-05,
76
- "loss": 1.0495,
77
- "step": 1000
78
- },
79
- {
80
- "epoch": 2.91,
81
- "eval_loss": 0.33204758167266846,
82
- "eval_runtime": 139.9575,
83
- "eval_samples_per_second": 33.01,
84
- "eval_steps_per_second": 4.13,
85
- "eval_wer": 0.28963470599033225,
86
- "step": 1000
87
- }
88
- ],
89
- "max_steps": 17200,
90
- "num_train_epochs": 50,
91
- "total_flos": 2.9636799545011507e+18,
92
- "trial_name": null,
93
- "trial_params": null
94
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0efc7aad7fd151e94de194f50e712cd8d3c82a2cf2ccee51d253c9130af43c3a
3
- size 2991
 
 
 
 
checkpoint-1500/config.json DELETED
@@ -1,107 +0,0 @@
1
- {
2
- "_name_or_path": "marinone94/xls-r-300m-sv-robust",
3
- "activation_dropout": 0.1,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
- "apply_spec_augment": true,
8
- "architectures": [
9
- "Wav2Vec2ForCTC"
10
- ],
11
- "attention_dropout": 0.0,
12
- "bos_token_id": 1,
13
- "classifier_proj_size": 256,
14
- "codevector_dim": 768,
15
- "contrastive_logits_temperature": 0.1,
16
- "conv_bias": true,
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": "mean",
45
- "ctc_zero_infinity": false,
46
- "diversity_loss_weight": 0.1,
47
- "do_stable_layer_norm": true,
48
- "eos_token_id": 2,
49
- "feat_extract_activation": "gelu",
50
- "feat_extract_dropout": 0.0,
51
- "feat_extract_norm": "layer",
52
- "feat_proj_dropout": 0.0,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "hidden_act": "gelu",
56
- "hidden_dropout": 0.0,
57
- "hidden_size": 1024,
58
- "initializer_range": 0.02,
59
- "intermediate_size": 4096,
60
- "layer_norm_eps": 1e-05,
61
- "layerdrop": 0.0,
62
- "mask_feature_length": 64,
63
- "mask_feature_min_masks": 0,
64
- "mask_feature_prob": 0.25,
65
- "mask_time_length": 10,
66
- "mask_time_min_masks": 2,
67
- "mask_time_prob": 0.75,
68
- "model_type": "wav2vec2",
69
- "num_adapter_layers": 3,
70
- "num_attention_heads": 16,
71
- "num_codevector_groups": 2,
72
- "num_codevectors_per_group": 320,
73
- "num_conv_pos_embedding_groups": 16,
74
- "num_conv_pos_embeddings": 128,
75
- "num_feat_extract_layers": 7,
76
- "num_hidden_layers": 24,
77
- "num_negatives": 100,
78
- "output_hidden_size": 1024,
79
- "pad_token_id": 34,
80
- "proj_codevector_dim": 768,
81
- "tdnn_dilation": [
82
- 1,
83
- 2,
84
- 3,
85
- 1,
86
- 1
87
- ],
88
- "tdnn_dim": [
89
- 512,
90
- 512,
91
- 512,
92
- 512,
93
- 1500
94
- ],
95
- "tdnn_kernel": [
96
- 5,
97
- 3,
98
- 3,
99
- 1,
100
- 1
101
- ],
102
- "torch_dtype": "float32",
103
- "transformers_version": "4.16.0.dev0",
104
- "use_weighted_layer_sum": false,
105
- "vocab_size": 37,
106
- "xvector_output_dim": 512
107
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b883c1f26bb60f965959e813f1fda3c9b0ed41e76a86ef50f71624403b758fb8
3
- size 2490362385
 
 
 
 
checkpoint-1500/preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
checkpoint-1500/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c440e5ae149a9c96063d6fceaaf311e4a73da0f507f9d87f6781437b8936e2e
3
- size 1262075377
 
 
 
 
checkpoint-1500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4982f7f3a3d3c9848cfac0ab0e4aff5b6f3cfec2ee0d2bf0be5471908380429e
3
- size 14503
 
 
 
 
checkpoint-1500/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:85136f3eae8581fb19c033614c8131d6fa5eb689dca190899d818b25b6fac92d
3
- size 559
 
 
 
 
checkpoint-1500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:15ccfdada89267f464b440ff4504b5d32a3dac17d15e8a8d5898e8ba842c4cbe
3
- size 623
 
 
 
 
checkpoint-1500/trainer_state.json DELETED
@@ -1,133 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 4.359680928208847,
5
- "global_step": 1500,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.29,
12
- "learning_rate": 3.675e-06,
13
- "loss": 1.0197,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 0.58,
18
- "learning_rate": 7.425e-06,
19
- "loss": 1.0171,
20
- "step": 200
21
- },
22
- {
23
- "epoch": 0.87,
24
- "learning_rate": 1.1137499999999998e-05,
25
- "loss": 1.026,
26
- "step": 300
27
- },
28
- {
29
- "epoch": 1.16,
30
- "learning_rate": 1.48875e-05,
31
- "loss": 1.0383,
32
- "step": 400
33
- },
34
- {
35
- "epoch": 1.45,
36
- "learning_rate": 1.86375e-05,
37
- "loss": 1.0296,
38
- "step": 500
39
- },
40
- {
41
- "epoch": 1.45,
42
- "eval_loss": 0.3191435635089874,
43
- "eval_runtime": 138.7872,
44
- "eval_samples_per_second": 33.288,
45
- "eval_steps_per_second": 4.165,
46
- "eval_wer": 0.27421526035611576,
47
- "step": 500
48
- },
49
- {
50
- "epoch": 1.74,
51
- "learning_rate": 2.23875e-05,
52
- "loss": 1.0529,
53
- "step": 600
54
- },
55
- {
56
- "epoch": 2.03,
57
- "learning_rate": 2.6137499999999995e-05,
58
- "loss": 1.0442,
59
- "step": 700
60
- },
61
- {
62
- "epoch": 2.32,
63
- "learning_rate": 2.9887499999999998e-05,
64
- "loss": 1.0632,
65
- "step": 800
66
- },
67
- {
68
- "epoch": 2.61,
69
- "learning_rate": 3.36375e-05,
70
- "loss": 1.037,
71
- "step": 900
72
- },
73
- {
74
- "epoch": 2.91,
75
- "learning_rate": 3.7387499999999994e-05,
76
- "loss": 1.0495,
77
- "step": 1000
78
- },
79
- {
80
- "epoch": 2.91,
81
- "eval_loss": 0.33204758167266846,
82
- "eval_runtime": 139.9575,
83
- "eval_samples_per_second": 33.01,
84
- "eval_steps_per_second": 4.13,
85
- "eval_wer": 0.28963470599033225,
86
- "step": 1000
87
- },
88
- {
89
- "epoch": 3.2,
90
- "learning_rate": 4.11375e-05,
91
- "loss": 1.0547,
92
- "step": 1100
93
- },
94
- {
95
- "epoch": 3.49,
96
- "learning_rate": 4.48875e-05,
97
- "loss": 1.06,
98
- "step": 1200
99
- },
100
- {
101
- "epoch": 3.78,
102
- "learning_rate": 4.8637499999999996e-05,
103
- "loss": 1.0655,
104
- "step": 1300
105
- },
106
- {
107
- "epoch": 4.07,
108
- "learning_rate": 5.23875e-05,
109
- "loss": 1.0757,
110
- "step": 1400
111
- },
112
- {
113
- "epoch": 4.36,
114
- "learning_rate": 5.61375e-05,
115
- "loss": 1.0532,
116
- "step": 1500
117
- },
118
- {
119
- "epoch": 4.36,
120
- "eval_loss": 0.344494104385376,
121
- "eval_runtime": 139.9249,
122
- "eval_samples_per_second": 33.018,
123
- "eval_steps_per_second": 4.131,
124
- "eval_wer": 0.2935201615370495,
125
- "step": 1500
126
- }
127
- ],
128
- "max_steps": 17200,
129
- "num_train_epochs": 50,
130
- "total_flos": 4.445118706030802e+18,
131
- "trial_name": null,
132
- "trial_params": null
133
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0efc7aad7fd151e94de194f50e712cd8d3c82a2cf2ccee51d253c9130af43c3a
3
- size 2991
 
 
 
 
checkpoint-500/.ipynb_checkpoints/trainer_state-checkpoint.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.4525018129079044,
5
- "global_step": 500,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.29,
12
- "learning_rate": 3.675e-06,
13
- "loss": 1.0197,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 0.58,
18
- "learning_rate": 7.425e-06,
19
- "loss": 1.0171,
20
- "step": 200
21
- },
22
- {
23
- "epoch": 0.87,
24
- "learning_rate": 1.1137499999999998e-05,
25
- "loss": 1.026,
26
- "step": 300
27
- },
28
- {
29
- "epoch": 1.16,
30
- "learning_rate": 1.48875e-05,
31
- "loss": 1.0383,
32
- "step": 400
33
- },
34
- {
35
- "epoch": 1.45,
36
- "learning_rate": 1.86375e-05,
37
- "loss": 1.0296,
38
- "step": 500
39
- },
40
- {
41
- "epoch": 1.45,
42
- "eval_loss": 0.3191435635089874,
43
- "eval_runtime": 138.7872,
44
- "eval_samples_per_second": 33.288,
45
- "eval_steps_per_second": 4.165,
46
- "eval_wer": 0.27421526035611576,
47
- "step": 500
48
- }
49
- ],
50
- "max_steps": 17200,
51
- "num_train_epochs": 50,
52
- "total_flos": 1.4827194756605722e+18,
53
- "trial_name": null,
54
- "trial_params": null
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-500/config.json DELETED
@@ -1,107 +0,0 @@
1
- {
2
- "_name_or_path": "marinone94/xls-r-300m-sv-robust",
3
- "activation_dropout": 0.1,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
- "apply_spec_augment": true,
8
- "architectures": [
9
- "Wav2Vec2ForCTC"
10
- ],
11
- "attention_dropout": 0.0,
12
- "bos_token_id": 1,
13
- "classifier_proj_size": 256,
14
- "codevector_dim": 768,
15
- "contrastive_logits_temperature": 0.1,
16
- "conv_bias": true,
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": "mean",
45
- "ctc_zero_infinity": false,
46
- "diversity_loss_weight": 0.1,
47
- "do_stable_layer_norm": true,
48
- "eos_token_id": 2,
49
- "feat_extract_activation": "gelu",
50
- "feat_extract_dropout": 0.0,
51
- "feat_extract_norm": "layer",
52
- "feat_proj_dropout": 0.0,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "hidden_act": "gelu",
56
- "hidden_dropout": 0.0,
57
- "hidden_size": 1024,
58
- "initializer_range": 0.02,
59
- "intermediate_size": 4096,
60
- "layer_norm_eps": 1e-05,
61
- "layerdrop": 0.0,
62
- "mask_feature_length": 64,
63
- "mask_feature_min_masks": 0,
64
- "mask_feature_prob": 0.25,
65
- "mask_time_length": 10,
66
- "mask_time_min_masks": 2,
67
- "mask_time_prob": 0.75,
68
- "model_type": "wav2vec2",
69
- "num_adapter_layers": 3,
70
- "num_attention_heads": 16,
71
- "num_codevector_groups": 2,
72
- "num_codevectors_per_group": 320,
73
- "num_conv_pos_embedding_groups": 16,
74
- "num_conv_pos_embeddings": 128,
75
- "num_feat_extract_layers": 7,
76
- "num_hidden_layers": 24,
77
- "num_negatives": 100,
78
- "output_hidden_size": 1024,
79
- "pad_token_id": 34,
80
- "proj_codevector_dim": 768,
81
- "tdnn_dilation": [
82
- 1,
83
- 2,
84
- 3,
85
- 1,
86
- 1
87
- ],
88
- "tdnn_dim": [
89
- 512,
90
- 512,
91
- 512,
92
- 512,
93
- 1500
94
- ],
95
- "tdnn_kernel": [
96
- 5,
97
- 3,
98
- 3,
99
- 1,
100
- 1
101
- ],
102
- "torch_dtype": "float32",
103
- "transformers_version": "4.16.0.dev0",
104
- "use_weighted_layer_sum": false,
105
- "vocab_size": 37,
106
- "xvector_output_dim": 512
107
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:11d7b3b64b03807fa1443a1bbb6c48b3760f1488bdb1c3d2a04da0de2ef280a6
3
- size 2490362385
 
 
 
 
checkpoint-500/preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
checkpoint-500/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:849f22348838353270f3fea71da7123aea0c4d81f944d73fe8359395ee3e8678
3
- size 1262075377
 
 
 
 
checkpoint-500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b82ac75b07e68dc3bc90e76f55a339f64dce724d87a9ae3c69ee46df441867
3
- size 14503
 
 
 
 
checkpoint-500/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c42d0f35980b579693b6d665e1977f1cb989811c56ccb359dcaf6fac0e92a29d
3
- size 559
 
 
 
 
checkpoint-500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ea5e90d46886b0a7f8061d0a93792e2f7c6219a21813faad05be67fa21d1a40
3
- size 623
 
 
 
 
checkpoint-500/trainer_state.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.4525018129079044,
5
- "global_step": 500,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.29,
12
- "learning_rate": 3.675e-06,
13
- "loss": 1.0197,
14
- "step": 100
15
- },
16
- {
17
- "epoch": 0.58,
18
- "learning_rate": 7.425e-06,
19
- "loss": 1.0171,
20
- "step": 200
21
- },
22
- {
23
- "epoch": 0.87,
24
- "learning_rate": 1.1137499999999998e-05,
25
- "loss": 1.026,
26
- "step": 300
27
- },
28
- {
29
- "epoch": 1.16,
30
- "learning_rate": 1.48875e-05,
31
- "loss": 1.0383,
32
- "step": 400
33
- },
34
- {
35
- "epoch": 1.45,
36
- "learning_rate": 1.86375e-05,
37
- "loss": 1.0296,
38
- "step": 500
39
- },
40
- {
41
- "epoch": 1.45,
42
- "eval_loss": 0.3191435635089874,
43
- "eval_runtime": 138.7872,
44
- "eval_samples_per_second": 33.288,
45
- "eval_steps_per_second": 4.165,
46
- "eval_wer": 0.27421526035611576,
47
- "step": 500
48
- }
49
- ],
50
- "max_steps": 17200,
51
- "num_train_epochs": 50,
52
- "total_flos": 1.4827194756605722e+18,
53
- "trial_name": null,
54
- "trial_params": null
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0efc7aad7fd151e94de194f50e712cd8d3c82a2cf2ccee51d253c9130af43c3a
3
- size 2991