Hugging Face's logo

SushantGautam
/
SoccerSum-NarSum

Transformers
PyTorch
English
led
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
SushantGautam commited on
Commit
b7b86ec
·
1 Parent(s): 4e1f4ac

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. config.json +2 -1
  3. pytorch_model.bin +2 -2
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +61 -49
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +67 -55
  8. training_args.bin +1 -1
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -36,6 +36,7 @@
36
  "encoder_layerdrop": 0.0,
37
  "encoder_layers": 12,
38
  "eos_token_id": 2,
 
39
  "gradient_checkpointing": false,
40
  "id2label": {
41
  "0": "LABEL_0",
@@ -59,5 +60,5 @@
59
  "torch_dtype": "float32",
60
  "transformers_version": "4.21.0.dev0",
61
  "use_cache": true,
62
- "vocab_size": 50265
63
  }
 
36
  "encoder_layerdrop": 0.0,
37
  "encoder_layers": 12,
38
  "eos_token_id": 2,
39
+ "forced_bos_token_id": 250004,
40
  "gradient_checkpointing": false,
41
  "id2label": {
42
  "0": "LABEL_0",
 
60
  "torch_dtype": "float32",
61
  "transformers_version": "4.21.0.dev0",
62
  "use_cache": true,
63
+ "vocab_size": 250054
64
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e4c085cc36dbd48584606a50743761a69fa1f26bc3813c4bda6d9c64aec0c28
3
- size 1839604721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59b9e75d271dcd9eddf637dd60cdfd3cd415e0ef6ef56711529b7ab85482b3c
3
+ size 2658739697
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json CHANGED
@@ -1,51 +1,63 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
 
 
 
 
 
 
 
 
 
 
 
 
51
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,30 +1,61 @@
1
  {
2
- "add_prefix_space": false,
3
- "bos_token": {
4
- "__type": "AddedToken",
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false
10
- },
11
- "cls_token": {
12
- "__type": "AddedToken",
13
- "content": "<s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "eos_token": {
20
- "__type": "AddedToken",
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
- "errors": "replace",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "mask_token": {
29
  "__type": "AddedToken",
30
  "content": "<mask>",
@@ -33,33 +64,14 @@
33
  "rstrip": false,
34
  "single_word": false
35
  },
36
- "model_max_length": 16384,
37
- "name_or_path": "allenai/led-large-16384",
38
- "pad_token": {
39
- "__type": "AddedToken",
40
- "content": "<pad>",
41
- "lstrip": false,
42
- "normalized": true,
43
- "rstrip": false,
44
- "single_word": false
45
- },
46
- "sep_token": {
47
- "__type": "AddedToken",
48
- "content": "</s>",
49
- "lstrip": false,
50
- "normalized": true,
51
- "rstrip": false,
52
- "single_word": false
53
- },
54
- "special_tokens_map_file": "/home/sushant/.cache/huggingface/transformers/2ad921573d53ebf0c0450d63a211e61d8e328324e84830c365abff01f2d115f1.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0",
55
- "tokenizer_class": "LEDTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": {
58
- "__type": "AddedToken",
59
- "content": "<unk>",
60
- "lstrip": false,
61
- "normalized": true,
62
- "rstrip": false,
63
- "single_word": false
64
- }
65
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
  "mask_token": {
60
  "__type": "AddedToken",
61
  "content": "<mask>",
 
64
  "rstrip": false,
65
  "single_word": false
66
  },
67
+ "model_max_length": 1024,
68
+ "name_or_path": "facebook/mbart-large-50",
69
+ "pad_token": "<pad>",
70
+ "sep_token": "</s>",
71
+ "sp_model_kwargs": {},
72
+ "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
73
+ "src_lang": null,
74
+ "tgt_lang": null,
75
+ "tokenizer_class": "MBart50Tokenizer",
76
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd2bdd52f5a1cf2c334cbbbbdce5bca3b83fe8eb3dbdf68484addbf3e3d0f71d
3
  size 3567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e77fcd6d6286fa4d42a66787ca60cbbe08d442aba6790c51043400a36ab384
3
  size 3567