Hugging Face's logo

marinone94
/
xls-r-300m-sv-robust

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
mozilla-foundation/common_voice_9_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
marinone94 commited on
Commit
70717e9
·
1 Parent(s): be82ea0

End of training

Browse files
Files changed (14) hide show
  1. all_results.json +14 -0
  2. checkpoint-1500/config.json +107 -0
  3. checkpoint-1500/optimizer.pt +3 -0
  4. checkpoint-1500/preprocessor_config.json +9 -0
  5. checkpoint-1500/pytorch_model.bin +3 -0
  6. checkpoint-1500/rng_state.pth +3 -0
  7. checkpoint-1500/scaler.pt +3 -0
  8. checkpoint-1500/scheduler.pt +3 -0
  9. checkpoint-1500/trainer_state.json +133 -0
  10. checkpoint-1500/training_args.bin +3 -0
  11. eval_results.json +9 -0
  12. pytorch_model.bin +1 -1
  13. train_results.json +8 -0
  14. trainer_state.json +154 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.5562844276428223,
4
+ "eval_runtime": 125.7791,
5
+ "eval_samples": 4620,
6
+ "eval_samples_per_second": 36.731,
7
+ "eval_steps_per_second": 4.595,
8
+ "eval_wer": 0.9487242244385976,
9
+ "train_loss": 2.7439405862675157,
10
+ "train_runtime": 3003.9637,
11
+ "train_samples": 11030,
12
+ "train_samples_per_second": 18.359,
13
+ "train_steps_per_second": 0.573
14
+ }
checkpoint-1500/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2927b1e7a6af7703304a15b14ed79cddd8a561ab70c3f1630c008c3debc0ac
3
+ size 2490362385
checkpoint-1500/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": true,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c146bd2ad9f313033c049f506c561ba8fa40b130d16254cb640b46a8117068a2
3
+ size 1262075377
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4982f7f3a3d3c9848cfac0ab0e4aff5b6f3cfec2ee0d2bf0be5471908380429e
3
+ size 14503
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75859b6f10fc5cb61ebf19c5b9211484a9a37deea8e552cb0ba6fc98b090d7ff
3
+ size 559
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4efdd67f0b22b26bc682e2f487b713df4629fa5b02c99d86373db7c1edd7d2a
3
+ size 623
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 7.151470588235293e-05,
13
+ "loss": 5.1135,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.58,
18
+ "learning_rate": 6.710294117647058e-05,
19
+ "loss": 3.0957,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.87,
24
+ "learning_rate": 6.269117647058824e-05,
25
+ "loss": 3.0078,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 1.16,
30
+ "learning_rate": 5.827941176470588e-05,
31
+ "loss": 2.9785,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 1.45,
36
+ "learning_rate": 5.3867647058823525e-05,
37
+ "loss": 2.9069,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 1.45,
42
+ "eval_loss": 2.9046826362609863,
43
+ "eval_runtime": 128.7688,
44
+ "eval_samples_per_second": 35.878,
45
+ "eval_steps_per_second": 4.489,
46
+ "eval_wer": 1.0,
47
+ "step": 500
48
+ },
49
+ {
50
+ "epoch": 1.74,
51
+ "learning_rate": 4.945588235294117e-05,
52
+ "loss": 2.8537,
53
+ "step": 600
54
+ },
55
+ {
56
+ "epoch": 2.03,
57
+ "learning_rate": 4.504411764705882e-05,
58
+ "loss": 2.7928,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 2.32,
63
+ "learning_rate": 4.063235294117647e-05,
64
+ "loss": 2.6988,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 2.61,
69
+ "learning_rate": 3.6220588235294115e-05,
70
+ "loss": 2.6342,
71
+ "step": 900
72
+ },
73
+ {
74
+ "epoch": 2.91,
75
+ "learning_rate": 3.180882352941176e-05,
76
+ "loss": 2.5875,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 2.91,
81
+ "eval_loss": 2.415876865386963,
82
+ "eval_runtime": 164.5912,
83
+ "eval_samples_per_second": 28.07,
84
+ "eval_steps_per_second": 3.512,
85
+ "eval_wer": 1.199687939790736,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 3.2,
90
+ "learning_rate": 2.739705882352941e-05,
91
+ "loss": 2.5214,
92
+ "step": 1100
93
+ },
94
+ {
95
+ "epoch": 3.49,
96
+ "learning_rate": 2.2985294117647057e-05,
97
+ "loss": 2.4174,
98
+ "step": 1200
99
+ },
100
+ {
101
+ "epoch": 3.78,
102
+ "learning_rate": 1.8573529411764705e-05,
103
+ "loss": 2.3271,
104
+ "step": 1300
105
+ },
106
+ {
107
+ "epoch": 4.07,
108
+ "learning_rate": 1.416176470588235e-05,
109
+ "loss": 2.2784,
110
+ "step": 1400
111
+ },
112
+ {
113
+ "epoch": 4.36,
114
+ "learning_rate": 9.75e-06,
115
+ "loss": 2.2043,
116
+ "step": 1500
117
+ },
118
+ {
119
+ "epoch": 4.36,
120
+ "eval_loss": 1.6191935539245605,
121
+ "eval_runtime": 127.3244,
122
+ "eval_samples_per_second": 36.285,
123
+ "eval_steps_per_second": 4.54,
124
+ "eval_wer": 0.9597993024536499,
125
+ "step": 1500
126
+ }
127
+ ],
128
+ "max_steps": 1720,
129
+ "num_train_epochs": 5,
130
+ "total_flos": 4.445118706030802e+18,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1208f22bb7e06e1e9a51692db0520fbddfc3640941d51dfe45ba3188ada2ecbf
3
+ size 2991
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.5562844276428223,
4
+ "eval_runtime": 125.7791,
5
+ "eval_samples": 4620,
6
+ "eval_samples_per_second": 36.731,
7
+ "eval_steps_per_second": 4.595,
8
+ "eval_wer": 0.9487242244385976
9
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aca4a6284adca4d75ba2f01b265d187999f0c8e97b09264b7de0ae8d1cf8e73
3
  size 1262075377
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22fe96372581760966d6d3482ae1d1974fb3aaebb6f1e041246fb9b3244f3ef
3
  size 1262075377
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 2.7439405862675157,
4
+ "train_runtime": 3003.9637,
5
+ "train_samples": 11030,
6
+ "train_samples_per_second": 18.359,
7
+ "train_steps_per_second": 0.573
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.9978245105148655,
5
+ "global_step": 1720,
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": 7.151470588235293e-05,
13
+ "loss": 5.1135,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.58,
18
+ "learning_rate": 6.710294117647058e-05,
19
+ "loss": 3.0957,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.87,
24
+ "learning_rate": 6.269117647058824e-05,
25
+ "loss": 3.0078,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 1.16,
30
+ "learning_rate": 5.827941176470588e-05,
31
+ "loss": 2.9785,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 1.45,
36
+ "learning_rate": 5.3867647058823525e-05,
37
+ "loss": 2.9069,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 1.45,
42
+ "eval_loss": 2.9046826362609863,
43
+ "eval_runtime": 128.7688,
44
+ "eval_samples_per_second": 35.878,
45
+ "eval_steps_per_second": 4.489,
46
+ "eval_wer": 1.0,
47
+ "step": 500
48
+ },
49
+ {
50
+ "epoch": 1.74,
51
+ "learning_rate": 4.945588235294117e-05,
52
+ "loss": 2.8537,
53
+ "step": 600
54
+ },
55
+ {
56
+ "epoch": 2.03,
57
+ "learning_rate": 4.504411764705882e-05,
58
+ "loss": 2.7928,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 2.32,
63
+ "learning_rate": 4.063235294117647e-05,
64
+ "loss": 2.6988,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 2.61,
69
+ "learning_rate": 3.6220588235294115e-05,
70
+ "loss": 2.6342,
71
+ "step": 900
72
+ },
73
+ {
74
+ "epoch": 2.91,
75
+ "learning_rate": 3.180882352941176e-05,
76
+ "loss": 2.5875,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 2.91,
81
+ "eval_loss": 2.415876865386963,
82
+ "eval_runtime": 164.5912,
83
+ "eval_samples_per_second": 28.07,
84
+ "eval_steps_per_second": 3.512,
85
+ "eval_wer": 1.199687939790736,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 3.2,
90
+ "learning_rate": 2.739705882352941e-05,
91
+ "loss": 2.5214,
92
+ "step": 1100
93
+ },
94
+ {
95
+ "epoch": 3.49,
96
+ "learning_rate": 2.2985294117647057e-05,
97
+ "loss": 2.4174,
98
+ "step": 1200
99
+ },
100
+ {
101
+ "epoch": 3.78,
102
+ "learning_rate": 1.8573529411764705e-05,
103
+ "loss": 2.3271,
104
+ "step": 1300
105
+ },
106
+ {
107
+ "epoch": 4.07,
108
+ "learning_rate": 1.416176470588235e-05,
109
+ "loss": 2.2784,
110
+ "step": 1400
111
+ },
112
+ {
113
+ "epoch": 4.36,
114
+ "learning_rate": 9.75e-06,
115
+ "loss": 2.2043,
116
+ "step": 1500
117
+ },
118
+ {
119
+ "epoch": 4.36,
120
+ "eval_loss": 1.6191935539245605,
121
+ "eval_runtime": 127.3244,
122
+ "eval_samples_per_second": 36.285,
123
+ "eval_steps_per_second": 4.54,
124
+ "eval_wer": 0.9597993024536499,
125
+ "step": 1500
126
+ },
127
+ {
128
+ "epoch": 4.65,
129
+ "learning_rate": 5.338235294117647e-06,
130
+ "loss": 2.1805,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 4.94,
135
+ "learning_rate": 9.26470588235294e-07,
136
+ "loss": 2.164,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 5.0,
141
+ "step": 1720,
142
+ "total_flos": 5.074147598591555e+18,
143
+ "train_loss": 2.7439405862675157,
144
+ "train_runtime": 3003.9637,
145
+ "train_samples_per_second": 18.359,
146
+ "train_steps_per_second": 0.573
147
+ }
148
+ ],
149
+ "max_steps": 1720,
150
+ "num_train_epochs": 5,
151
+ "total_flos": 5.074147598591555e+18,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }