Hugging Face's logo

summervent
/
russian-spellchecking3

Transformers
PyTorch
TensorBoard
t5
text2text-generation
text-generation-inference
Model card Files
xet
 Metrics Community
1
summervent commited on
Commit
1a42ae5
·
1 Parent(s): af96992

Training in progress, step 500

Browse files
Files changed (15) hide show
  1. .gitignore +1 -0
  2. config.json +62 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jan27_15-19-38_a3492d7d289e/1674832781.8921645/events.out.tfevents.1674832781.a3492d7d289e.341.7 +3 -0
  5. runs/Jan27_15-19-38_a3492d7d289e/events.out.tfevents.1674832781.a3492d7d289e.341.6 +3 -0
  6. runs1/Jan27_15-17-21_a3492d7d289e/1674832644.8814478/events.out.tfevents.1674832644.a3492d7d289e.341.5 +3 -0
  7. runs1/Jan27_15-17-21_a3492d7d289e/events.out.tfevents.1674832644.a3492d7d289e.341.4 +3 -0
  8. runs_/Jan27_14-57-07_a3492d7d289e/1674831434.5593822/events.out.tfevents.1674831434.a3492d7d289e.341.1 +3 -0
  9. runs_/Jan27_14-57-07_a3492d7d289e/events.out.tfevents.1674831434.a3492d7d289e.341.0 +3 -0
  10. runs_/Jan27_15-13-14_a3492d7d289e/1674832398.2754402/events.out.tfevents.1674832398.a3492d7d289e.341.3 +3 -0
  11. runs_/Jan27_15-13-14_a3492d7d289e/events.out.tfevents.1674832398.a3492d7d289e.341.2 +3 -0
  12. special_tokens_map.json +107 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +113 -0
  15. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "UrukHan/t5-russian-spell",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "T5ForConditionalGeneration"
6
+ ],
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "max_length": 256,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "task_specific_params": {
30
+ "summarization": {
31
+ "early_stopping": true,
32
+ "length_penalty": 2.0,
33
+ "max_length": 200,
34
+ "min_length": 30,
35
+ "no_repeat_ngram_size": 3,
36
+ "num_beams": 4,
37
+ "prefix": "summarize: "
38
+ },
39
+ "translation_en_to_de": {
40
+ "early_stopping": true,
41
+ "max_length": 300,
42
+ "num_beams": 4,
43
+ "prefix": "translate English to German: "
44
+ },
45
+ "translation_en_to_fr": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to French: "
50
+ },
51
+ "translation_en_to_ro": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to Romanian: "
56
+ }
57
+ },
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.26.0",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e6c222664f47e53d95a373ba16c4cde65d70e68d5d11f14f2a78880b730252
3
+ size 891702929
runs/Jan27_15-19-38_a3492d7d289e/1674832781.8921645/events.out.tfevents.1674832781.a3492d7d289e.341.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574ae325413ecfc0a0fd5c7b707547f88344d9a94f5fa25d27d0d89acf8a2a03
3
+ size 5921
runs/Jan27_15-19-38_a3492d7d289e/events.out.tfevents.1674832781.a3492d7d289e.341.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd80b812d69b7be9577a74b6eae27f75a30f40e4b362722d90d2052652047b2
3
+ size 7613
runs1/Jan27_15-17-21_a3492d7d289e/1674832644.8814478/events.out.tfevents.1674832644.a3492d7d289e.341.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7bcc92335cbaa395da589679e0c44c03a3ea9adb15e239bbfd9d91b3068776
3
+ size 5921
runs1/Jan27_15-17-21_a3492d7d289e/events.out.tfevents.1674832644.a3492d7d289e.341.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d25a57d1978e2ec7ec41265742050fba5f49c095bec3a0942ced94d0075a4e
3
+ size 4841
runs_/Jan27_14-57-07_a3492d7d289e/1674831434.5593822/events.out.tfevents.1674831434.a3492d7d289e.341.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef70e3cc26982f12b1838f186d5ca076847be0a9e79fd46094bd1d181550b1c
3
+ size 5921
runs_/Jan27_14-57-07_a3492d7d289e/events.out.tfevents.1674831434.a3492d7d289e.341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08bb7ad9c2b7b36dc1fdac1a8dd47d3ca6ebf3e8e2e61bed9e2b3943d8c0f923
3
+ size 5354
runs_/Jan27_15-13-14_a3492d7d289e/1674832398.2754402/events.out.tfevents.1674832398.a3492d7d289e.341.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3973c098b0262096eeef4b047d82fbf14265f36ab004ddfc3769020ed316e291
3
+ size 5921
runs_/Jan27_15-13-14_a3492d7d289e/events.out.tfevents.1674832398.a3492d7d289e.341.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a094937e91afe1a5af3e02564a83ac8097807425ba0249bef7a7cbb4b1db223c
3
+ size 4841
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 1000000000000000019884624838656,
107
+ "name_or_path": "UrukHan/t5-russian-spell",
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "special_tokens_map_file": null,
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3da95b42fc5ecb5c728ee8c8a23484a0527238031fb2265e5f0c142b7633fd
3
+ size 3643