prithviraj-maurya commited on
Commit
c8bd869
1 Parent(s): 8fc63f9

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 50264,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
+ }
config.json CHANGED
@@ -1,61 +1,73 @@
1
  {
2
- "_name_or_path": "t5-base",
 
 
 
 
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
 
 
 
6
  "classifier_dropout": 0.0,
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": 1,
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
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
- "output_past": true,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
 
 
28
  "task_specific_params": {
29
  "summarization": {
30
- "early_stopping": true,
31
- "length_penalty": 2.0,
32
- "max_length": 200,
33
- "min_length": 30,
34
- "no_repeat_ngram_size": 3,
35
- "num_beams": 4,
36
- "prefix": "summarize: "
37
  },
38
- "translation_en_to_de": {
39
- "early_stopping": true,
40
- "max_length": 300,
41
- "num_beams": 4,
42
- "prefix": "translate English to German: "
43
- },
44
- "translation_en_to_fr": {
45
- "early_stopping": true,
46
- "max_length": 300,
47
- "num_beams": 4,
48
- "prefix": "translate English to French: "
49
  },
50
- "translation_en_to_ro": {
51
- "early_stopping": true,
52
- "max_length": 300,
53
- "num_beams": 4,
54
- "prefix": "translate English to Romanian: "
55
  }
56
  },
57
  "torch_dtype": "float32",
58
- "transformers_version": "4.33.3",
59
  "use_cache": true,
60
- "vocab_size": 32128
61
  }
 
1
  {
2
+ "_name_or_path": "eugenesiow/bart-paraphrase",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
  "architectures": [
8
+ "BartForConditionalGeneration"
9
  ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
  "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
  "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "num_beams": 4,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
  "task_specific_params": {
50
  "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
 
 
 
55
  },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
 
 
 
 
 
 
61
  },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
  }
68
  },
69
  "torch_dtype": "float32",
70
+ "transformers_version": "4.34.0",
71
  "use_cache": true,
72
+ "vocab_size": 50265
73
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:186812ffe9b57b299ac0760f8e63c1852ca9ae24bf8b9eb83317b6aad5a49dba
3
- size 891702929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f22fe65d0b6237a28967ca76a4b78790519d681bebb30fd57115ce64f23e2f6
3
+ size 1625541389
special_tokens_map.json CHANGED
@@ -1,107 +1,9 @@
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
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
  "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
  "unk_token": "<unk>"
9
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,112 +1,66 @@
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
  "clean_up_tokenization_spaces": true,
 
105
  "eos_token": "</s>",
106
- "extra_ids": 100,
107
- "model_max_length": 512,
 
 
 
108
  "pad_token": "<pad>",
 
 
109
  "return_tensors": "pt",
110
- "tokenizer_class": "T5Tokenizer",
 
 
 
 
 
111
  "unk_token": "<unk>"
112
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [],
46
+ "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
  "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "max_length": 128,
53
+ "model_max_length": 1024,
54
+ "pad_to_multiple_of": null,
55
  "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
  "return_tensors": "pt",
59
+ "sep_token": "</s>",
60
+ "stride": 0,
61
+ "tokenizer_class": "BartTokenizer",
62
+ "trim_offsets": true,
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
  "unk_token": "<unk>"
66
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a941bfba76a7e0ad8ae56402a8796066f21c138807cc6a3a1d82901df58280
3
- size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7c968eb319aadafe122f303ce673442d84507c0b34ba34b0293ec42a208081
3
+ size 4219
vocab.json ADDED
The diff for this file is too large to render. See raw diff