dhivyeshrk commited on
Commit
dce2134
1 Parent(s): 69a0495

Training done for bart-cnn

Browse files
config.json CHANGED
@@ -1,29 +1,33 @@
1
  {
2
- "_name_or_path": "google/pegasus-cnn_dailymail",
3
- "activation_dropout": 0.1,
4
- "activation_function": "relu",
5
- "add_bias_logits": false,
6
- "add_final_layer_norm": true,
7
  "architectures": [
8
- "PegasusForConditionalGeneration"
9
  ],
10
- "attention_dropout": 0.1,
11
  "bos_token_id": 0,
12
  "classif_dropout": 0.0,
 
13
  "d_model": 1024,
14
  "decoder_attention_heads": 16,
15
  "decoder_ffn_dim": 4096,
16
  "decoder_layerdrop": 0.0,
17
- "decoder_layers": 16,
18
- "decoder_start_token_id": 0,
19
  "dropout": 0.1,
 
20
  "encoder_attention_heads": 16,
21
  "encoder_ffn_dim": 4096,
22
  "encoder_layerdrop": 0.0,
23
- "encoder_layers": 16,
24
- "eos_token_id": 1,
25
- "extra_pos_embeddings": 1,
26
- "forced_eos_token_id": 1,
 
 
27
  "id2label": {
28
  "0": "LABEL_0",
29
  "1": "LABEL_1",
@@ -36,20 +40,31 @@
36
  "LABEL_1": 1,
37
  "LABEL_2": 2
38
  },
39
- "length_penalty": 0.8,
40
- "max_length": 128,
41
  "max_position_embeddings": 1024,
42
- "min_length": 32,
43
- "model_type": "pegasus",
44
- "normalize_before": true,
45
- "normalize_embedding": false,
46
- "num_beams": 8,
47
- "num_hidden_layers": 16,
48
- "pad_token_id": 0,
49
- "scale_embedding": true,
50
- "static_position_embeddings": true,
 
 
 
 
 
 
 
 
 
 
 
51
  "torch_dtype": "float32",
52
  "transformers_version": "4.30.2",
53
  "use_cache": true,
54
- "vocab_size": 96103
55
  }
 
1
  {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
  "architectures": [
8
+ "BartForConditionalGeneration"
9
  ],
10
+ "attention_dropout": 0.0,
11
  "bos_token_id": 0,
12
  "classif_dropout": 0.0,
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
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
  "id2label": {
32
  "0": "LABEL_0",
33
  "1": "LABEL_1",
 
40
  "LABEL_1": 1,
41
  "LABEL_2": 2
42
  },
43
+ "length_penalty": 2.0,
44
+ "max_length": 142,
45
  "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
  "torch_dtype": "float32",
67
  "transformers_version": "4.30.2",
68
  "use_cache": true,
69
+ "vocab_size": 50264
70
  }
generation_config.json CHANGED
@@ -1,13 +1,16 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
- "decoder_start_token_id": 0,
5
- "eos_token_id": 1,
6
- "forced_eos_token_id": 1,
7
- "length_penalty": 0.8,
8
- "max_length": 128,
9
- "min_length": 32,
10
- "num_beams": 8,
11
- "pad_token_id": 0,
 
 
 
12
  "transformers_version": "4.30.2"
13
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "length_penalty": 2.0,
10
+ "max_length": 142,
11
+ "min_length": 56,
12
+ "no_repeat_ngram_size": 3,
13
+ "num_beams": 4,
14
+ "pad_token_id": 1,
15
  "transformers_version": "4.30.2"
16
  }
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 sha256:142a5a7a5f27da3d8f2f9cbc826a66da1d3e7b6cc6ae247cea43bdc0a1457cf9
3
- size 2283804653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6feb19b1666c39bef49f58c85cea622cf7b11f809fd75744931e84806a46e2d
3
+ size 1625537293
special_tokens_map.json CHANGED
@@ -1,110 +1,15 @@
1
  {
2
- "additional_special_tokens": [
3
- "<mask_1>",
4
- "<unk_2>",
5
- "<unk_3>",
6
- "<unk_4>",
7
- "<unk_5>",
8
- "<unk_6>",
9
- "<unk_7>",
10
- "<unk_8>",
11
- "<unk_9>",
12
- "<unk_10>",
13
- "<unk_11>",
14
- "<unk_12>",
15
- "<unk_13>",
16
- "<unk_14>",
17
- "<unk_15>",
18
- "<unk_16>",
19
- "<unk_17>",
20
- "<unk_18>",
21
- "<unk_19>",
22
- "<unk_20>",
23
- "<unk_21>",
24
- "<unk_22>",
25
- "<unk_23>",
26
- "<unk_24>",
27
- "<unk_25>",
28
- "<unk_26>",
29
- "<unk_27>",
30
- "<unk_28>",
31
- "<unk_29>",
32
- "<unk_30>",
33
- "<unk_31>",
34
- "<unk_32>",
35
- "<unk_33>",
36
- "<unk_34>",
37
- "<unk_35>",
38
- "<unk_36>",
39
- "<unk_37>",
40
- "<unk_38>",
41
- "<unk_39>",
42
- "<unk_40>",
43
- "<unk_41>",
44
- "<unk_42>",
45
- "<unk_43>",
46
- "<unk_44>",
47
- "<unk_45>",
48
- "<unk_46>",
49
- "<unk_47>",
50
- "<unk_48>",
51
- "<unk_49>",
52
- "<unk_50>",
53
- "<unk_51>",
54
- "<unk_52>",
55
- "<unk_53>",
56
- "<unk_54>",
57
- "<unk_55>",
58
- "<unk_56>",
59
- "<unk_57>",
60
- "<unk_58>",
61
- "<unk_59>",
62
- "<unk_60>",
63
- "<unk_61>",
64
- "<unk_62>",
65
- "<unk_63>",
66
- "<unk_64>",
67
- "<unk_65>",
68
- "<unk_66>",
69
- "<unk_67>",
70
- "<unk_68>",
71
- "<unk_69>",
72
- "<unk_70>",
73
- "<unk_71>",
74
- "<unk_72>",
75
- "<unk_73>",
76
- "<unk_74>",
77
- "<unk_75>",
78
- "<unk_76>",
79
- "<unk_77>",
80
- "<unk_78>",
81
- "<unk_79>",
82
- "<unk_80>",
83
- "<unk_81>",
84
- "<unk_82>",
85
- "<unk_83>",
86
- "<unk_84>",
87
- "<unk_85>",
88
- "<unk_86>",
89
- "<unk_87>",
90
- "<unk_88>",
91
- "<unk_89>",
92
- "<unk_90>",
93
- "<unk_91>",
94
- "<unk_92>",
95
- "<unk_93>",
96
- "<unk_94>",
97
- "<unk_95>",
98
- "<unk_96>",
99
- "<unk_97>",
100
- "<unk_98>",
101
- "<unk_99>",
102
- "<unk_100>",
103
- "<unk_101>",
104
- "<unk_102>"
105
- ],
106
  "eos_token": "</s>",
107
- "mask_token": "<mask_2>",
 
 
 
 
 
 
108
  "pad_token": "<pad>",
 
109
  "unk_token": "<unk>"
110
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
  "unk_token": "<unk>"
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,117 +1,15 @@
1
  {
2
- "additional_special_tokens": [
3
- "<mask_1>",
4
- "<unk_2>",
5
- "<unk_3>",
6
- "<unk_4>",
7
- "<unk_5>",
8
- "<unk_6>",
9
- "<unk_7>",
10
- "<unk_8>",
11
- "<unk_9>",
12
- "<unk_10>",
13
- "<unk_11>",
14
- "<unk_12>",
15
- "<unk_13>",
16
- "<unk_14>",
17
- "<unk_15>",
18
- "<unk_16>",
19
- "<unk_17>",
20
- "<unk_18>",
21
- "<unk_19>",
22
- "<unk_20>",
23
- "<unk_21>",
24
- "<unk_22>",
25
- "<unk_23>",
26
- "<unk_24>",
27
- "<unk_25>",
28
- "<unk_26>",
29
- "<unk_27>",
30
- "<unk_28>",
31
- "<unk_29>",
32
- "<unk_30>",
33
- "<unk_31>",
34
- "<unk_32>",
35
- "<unk_33>",
36
- "<unk_34>",
37
- "<unk_35>",
38
- "<unk_36>",
39
- "<unk_37>",
40
- "<unk_38>",
41
- "<unk_39>",
42
- "<unk_40>",
43
- "<unk_41>",
44
- "<unk_42>",
45
- "<unk_43>",
46
- "<unk_44>",
47
- "<unk_45>",
48
- "<unk_46>",
49
- "<unk_47>",
50
- "<unk_48>",
51
- "<unk_49>",
52
- "<unk_50>",
53
- "<unk_51>",
54
- "<unk_52>",
55
- "<unk_53>",
56
- "<unk_54>",
57
- "<unk_55>",
58
- "<unk_56>",
59
- "<unk_57>",
60
- "<unk_58>",
61
- "<unk_59>",
62
- "<unk_60>",
63
- "<unk_61>",
64
- "<unk_62>",
65
- "<unk_63>",
66
- "<unk_64>",
67
- "<unk_65>",
68
- "<unk_66>",
69
- "<unk_67>",
70
- "<unk_68>",
71
- "<unk_69>",
72
- "<unk_70>",
73
- "<unk_71>",
74
- "<unk_72>",
75
- "<unk_73>",
76
- "<unk_74>",
77
- "<unk_75>",
78
- "<unk_76>",
79
- "<unk_77>",
80
- "<unk_78>",
81
- "<unk_79>",
82
- "<unk_80>",
83
- "<unk_81>",
84
- "<unk_82>",
85
- "<unk_83>",
86
- "<unk_84>",
87
- "<unk_85>",
88
- "<unk_86>",
89
- "<unk_87>",
90
- "<unk_88>",
91
- "<unk_89>",
92
- "<unk_90>",
93
- "<unk_91>",
94
- "<unk_92>",
95
- "<unk_93>",
96
- "<unk_94>",
97
- "<unk_95>",
98
- "<unk_96>",
99
- "<unk_97>",
100
- "<unk_98>",
101
- "<unk_99>",
102
- "<unk_100>",
103
- "<unk_101>",
104
- "<unk_102>"
105
- ],
106
  "clean_up_tokenization_spaces": true,
 
107
  "eos_token": "</s>",
108
- "full_tokenizer_file": null,
109
- "mask_token": "<mask_2>",
110
- "mask_token_sent": "<mask_1>",
111
  "model_max_length": 1024,
112
- "offset": 103,
113
  "pad_token": "<pad>",
114
- "sp_model_kwargs": {},
115
- "tokenizer_class": "PegasusTokenizer",
 
116
  "unk_token": "<unk>"
117
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
  "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
 
9
  "model_max_length": 1024,
 
10
  "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "BartTokenizer",
13
+ "trim_offsets": true,
14
  "unk_token": "<unk>"
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a973b37e1439b939bac2ecdb5c31a48c233b2af439ec0dc6abc1aa29f3f9b68d
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4743d5e9b7f51ae40868e0171134137befbaaf7b46649157a1761a39499150e3
3
  size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff