patrickvonplaten
commited on
Commit
·
f71d7df
1
Parent(s):
33b9026
End of training
Browse files- .gitignore +1 -0
- added_tokens.json +1 -0
- all_results.json +14 -0
- config.json +87 -0
- emissions.csv +2 -0
- eval_results.json +9 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Sep22_13-54-36_ip-172-31-1-149/1632318915.4067423/events.out.tfevents.1632318915.ip-172-31-1-149.2364014.1 +3 -0
- runs/Sep22_13-54-36_ip-172-31-1-149/events.out.tfevents.1632318915.ip-172-31-1-149.2364014.0 +3 -0
- runs/Sep22_13-54-36_ip-172-31-1-149/events.out.tfevents.1632318935.ip-172-31-1-149.2364014.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +115 -0
- training_args.bin +3 -0
- vocab.json +1 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 40, "</s>": 41}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"eval_loss": 15.181209564208984,
|
4 |
+
"eval_runtime": 1.0846,
|
5 |
+
"eval_samples": 9,
|
6 |
+
"eval_samples_per_second": 8.298,
|
7 |
+
"eval_steps_per_second": 0.922,
|
8 |
+
"eval_wer": 1.0,
|
9 |
+
"train_loss": 19.285240809122723,
|
10 |
+
"train_runtime": 17.2618,
|
11 |
+
"train_samples": 22,
|
12 |
+
"train_samples_per_second": 19.117,
|
13 |
+
"train_steps_per_second": 0.869
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
+
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
+
"conv_dim": [
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512
|
22 |
+
],
|
23 |
+
"conv_kernel": [
|
24 |
+
10,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
3,
|
29 |
+
2,
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"conv_stride": [
|
33 |
+
5,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2
|
40 |
+
],
|
41 |
+
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": false,
|
43 |
+
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
+
"eos_token_id": 2,
|
46 |
+
"feat_extract_activation": "gelu",
|
47 |
+
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
+
"feat_proj_dropout": 0.0,
|
50 |
+
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
52 |
+
"gradient_checkpointing": true,
|
53 |
+
"hidden_act": "gelu",
|
54 |
+
"hidden_dropout": 0.0,
|
55 |
+
"hidden_size": 1024,
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 4096,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.0,
|
60 |
+
"mask_channel_length": 10,
|
61 |
+
"mask_channel_min_space": 1,
|
62 |
+
"mask_channel_other": 0.0,
|
63 |
+
"mask_channel_prob": 0.0,
|
64 |
+
"mask_channel_selection": "static",
|
65 |
+
"mask_feature_length": 10,
|
66 |
+
"mask_feature_prob": 0.0,
|
67 |
+
"mask_time_length": 10,
|
68 |
+
"mask_time_min_space": 1,
|
69 |
+
"mask_time_other": 0.0,
|
70 |
+
"mask_time_prob": 0.05,
|
71 |
+
"mask_time_selection": "static",
|
72 |
+
"model_type": "wav2vec2",
|
73 |
+
"num_attention_heads": 16,
|
74 |
+
"num_codevector_groups": 2,
|
75 |
+
"num_codevectors_per_group": 320,
|
76 |
+
"num_conv_pos_embedding_groups": 16,
|
77 |
+
"num_conv_pos_embeddings": 128,
|
78 |
+
"num_feat_extract_layers": 7,
|
79 |
+
"num_hidden_layers": 24,
|
80 |
+
"num_negatives": 100,
|
81 |
+
"pad_token_id": 39,
|
82 |
+
"proj_codevector_dim": 768,
|
83 |
+
"torch_dtype": "float32",
|
84 |
+
"transformers_version": "4.11.0.dev0",
|
85 |
+
"use_weighted_layer_sum": false,
|
86 |
+
"vocab_size": 42
|
87 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
+
2021-09-22T13:55:32,ac9b9d44-9589-42ab-a5a2-0de5bc67ddc2,codecarbon,9.645862579345703,0.001182175545353683,0.0032141803843221397,USA,USA,nan,Y,aws,us-east-1
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"eval_loss": 15.181209564208984,
|
4 |
+
"eval_runtime": 1.0846,
|
5 |
+
"eval_samples": 9,
|
6 |
+
"eval_samples_per_second": 8.298,
|
7 |
+
"eval_steps_per_second": 0.922,
|
8 |
+
"eval_wer": 1.0
|
9 |
+
}
|
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 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:705e639e18462330243e495bd3ac30410332aada32d89a1362563f009c7f2b5a
|
3 |
+
size 1262095857
|
runs/Sep22_13-54-36_ip-172-31-1-149/1632318915.4067423/events.out.tfevents.1632318915.ip-172-31-1-149.2364014.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78a011816a6512c7e1cc19e265bc4375b17382a19cc2e5d240b9863ffe5b50ba
|
3 |
+
size 4457
|
runs/Sep22_13-54-36_ip-172-31-1-149/events.out.tfevents.1632318915.ip-172-31-1-149.2364014.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e99ac8282265646b70b6b4e405366a5cabbeb323a66bb5eabc408fc34931f07
|
3 |
+
size 7041
|
runs/Sep22_13-54-36_ip-172-31-1-149/events.out.tfevents.1632318935.ip-172-31-1-149.2364014.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ac41d13b001f09b28cdd8fb96e4e19738a013979b14f93e79c801ad98f7f98
|
3 |
+
size 352
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "././wav2vec2-common_voice-ab-demo", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"train_loss": 19.285240809122723,
|
4 |
+
"train_runtime": 17.2618,
|
5 |
+
"train_samples": 22,
|
6 |
+
"train_samples_per_second": 19.117,
|
7 |
+
"train_steps_per_second": 0.869
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 15,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 0.0,
|
13 |
+
"loss": 18.7924,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.0,
|
18 |
+
"learning_rate": 0.0,
|
19 |
+
"loss": 20.7055,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.0,
|
24 |
+
"learning_rate": 0.0,
|
25 |
+
"loss": 20.7584,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 4.0,
|
30 |
+
"learning_rate": 0.0,
|
31 |
+
"loss": 19.0565,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 5.0,
|
36 |
+
"learning_rate": 6e-07,
|
37 |
+
"loss": 19.4821,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 6.0,
|
42 |
+
"learning_rate": 1.2e-06,
|
43 |
+
"loss": 19.2156,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 7.0,
|
48 |
+
"learning_rate": 1.8e-06,
|
49 |
+
"loss": 18.2756,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 8.0,
|
54 |
+
"learning_rate": 2.4e-06,
|
55 |
+
"loss": 20.6991,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 9.0,
|
60 |
+
"learning_rate": 2.9999999999999997e-06,
|
61 |
+
"loss": 16.1652,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 10.0,
|
66 |
+
"learning_rate": 3.6e-06,
|
67 |
+
"loss": 19.7457,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 11.0,
|
72 |
+
"learning_rate": 4.2e-06,
|
73 |
+
"loss": 19.2072,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 12.0,
|
78 |
+
"learning_rate": 4.8e-06,
|
79 |
+
"loss": 16.8633,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 13.0,
|
84 |
+
"learning_rate": 5.399999999999999e-06,
|
85 |
+
"loss": 19.2082,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 14.0,
|
90 |
+
"learning_rate": 5.999999999999999e-06,
|
91 |
+
"loss": 20.4279,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 15.0,
|
96 |
+
"learning_rate": 6.599999999999999e-06,
|
97 |
+
"loss": 20.6761,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 15.0,
|
102 |
+
"step": 15,
|
103 |
+
"total_flos": 9.481946310220186e+16,
|
104 |
+
"train_loss": 19.285240809122723,
|
105 |
+
"train_runtime": 17.2618,
|
106 |
+
"train_samples_per_second": 19.117,
|
107 |
+
"train_steps_per_second": 0.869
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 15,
|
111 |
+
"num_train_epochs": 15,
|
112 |
+
"total_flos": 9.481946310220186e+16,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:064a1b01e8ea4f412d4fd83cd5f399592c01657c07a3ff0bd376292cf34daf3b
|
3 |
+
size 2863
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "к": 10, "л": 11, "м": 12, "н": 13, "о": 14, "п": 15, "р": 16, "с": 17, "т": 18, "у": 19, "ф": 20, "х": 21, "ц": 22, "ш": 23, "ы": 24, "ь": 25, "қ": 26, "ҟ": 27, "ҩ": 28, "ҭ": 29, "ҳ": 30, "ҵ": 31, "ҽ": 32, "ҿ": 33, "ә": 34, "ӡ": 35, "ӷ": 36, "ԥ": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}
|