Hugging Face's logo

theojolliffe
/
bart-ing-extract

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
theojolliffe commited on
Commit
8a821d4
·
1 Parent(s): 5f75867

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. config.json +45 -61
  2. pytorch_model.bin +2 -2
  3. runs/Aug09_19-12-46_61c9bf70029a/events.out.tfevents.1691608369.61c9bf70029a.31992.0 +2 -2
  4. runs/Aug09_20-22-34_61c9bf70029a/1691612587.3719232/events.out.tfevents.1691612587.61c9bf70029a.57273.1 +3 -0
  5. runs/Aug09_20-22-34_61c9bf70029a/events.out.tfevents.1691612587.61c9bf70029a.57273.0 +3 -0
  6. special_tokens_map.json +105 -49
  7. spiece.model +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +109 -60
  10. training_args.bin +1 -1
config.json CHANGED
@@ -1,77 +1,61 @@
1
  {
2
- "_name_or_path": "sshleifer/distilbart-cnn-12-6",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "gelu",
6
- "add_bias_logits": false,
7
- "add_final_layer_norm": false,
8
  "architectures": [
9
- "BartForConditionalGeneration"
10
  ],
11
- "attention_dropout": 0.0,
12
- "bos_token_id": 0,
13
- "classif_dropout": 0.0,
14
- "classifier_dropout": 0.0,
15
- "d_model": 1024,
16
- "decoder_attention_heads": 16,
17
- "decoder_ffn_dim": 4096,
18
- "decoder_layerdrop": 0.0,
19
- "decoder_layers": 6,
20
- "decoder_start_token_id": 2,
21
- "dropout": 0.1,
22
- "early_stopping": true,
23
- "encoder_attention_heads": 16,
24
- "encoder_ffn_dim": 4096,
25
- "encoder_layerdrop": 0.0,
26
- "encoder_layers": 12,
27
- "eos_token_id": 2,
28
- "extra_pos_embeddings": 2,
29
- "force_bos_token_to_be_generated": true,
30
- "forced_bos_token_id": 0,
31
- "forced_eos_token_id": 2,
32
- "gradient_checkpointing": false,
33
- "id2label": {
34
- "0": "LABEL_0",
35
- "1": "LABEL_1",
36
- "2": "LABEL_2"
37
- },
38
- "init_std": 0.02,
39
  "is_encoder_decoder": true,
40
- "label2id": {
41
- "LABEL_0": 0,
42
- "LABEL_1": 1,
43
- "LABEL_2": 2
44
- },
45
- "length_penalty": 2.0,
46
- "max_length": 142,
47
- "max_position_embeddings": 1024,
48
- "min_length": 56,
49
- "model_type": "bart",
50
- "no_repeat_ngram_size": 3,
51
- "normalize_before": false,
52
- "normalize_embedding": true,
53
- "num_beams": 4,
54
- "num_hidden_layers": 12,
55
  "output_past": true,
56
- "pad_token_id": 1,
57
- "prefix": " ",
58
- "replacing_rate": 0,
59
- "scale_embedding": false,
60
- "static_position_embeddings": false,
61
- "student_decoder_layers": null,
62
- "student_encoder_layers": null,
63
  "task_specific_params": {
64
  "summarization": {
65
  "early_stopping": true,
66
  "length_penalty": 2.0,
67
- "max_length": 142,
68
- "min_length": 56,
69
  "no_repeat_ngram_size": 3,
70
- "num_beams": 4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
  }
72
  },
 
73
  "torch_dtype": "float32",
74
  "transformers_version": "4.28.0",
75
  "use_cache": true,
76
- "vocab_size": 50264
77
  }
 
1
  {
2
+ "_name_or_path": "google/flan-t5-small",
 
 
 
 
 
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
 
 
 
 
 
 
 
 
23
  "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
 
 
 
 
27
  "task_specific_params": {
28
  "summarization": {
29
  "early_stopping": true,
30
  "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
  "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
  }
55
  },
56
+ "tie_word_embeddings": false,
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.28.0",
59
  "use_cache": true,
60
+ "vocab_size": 32128
61
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bad4bfca566ebe02e4829b51f8e7f00a977abfacd6b8c6fcadcc7a271953670
3
- size 1222363741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61e25eb29b9917691bb35646a92c3f398d03c9bf45976973ce7c3d5a5fa8fe0
3
+ size 307910149
runs/Aug09_19-12-46_61c9bf70029a/events.out.tfevents.1691608369.61c9bf70029a.31992.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d52b8a07003a308c9c42c01451cb7e00e678a86d6520f47fbaeb85d08f22166
3
- size 7710
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285cf693b87cc29b52e9654f99a2fc840614dd45cc20e89aeae9e3f3818c276b
3
+ size 8589
runs/Aug09_20-22-34_61c9bf70029a/1691612587.3719232/events.out.tfevents.1691612587.61c9bf70029a.57273.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd4078a21b0e70dd2f359ab6b300a7d18c8e89b8d98ae040fd20c094bd7daba7
3
+ size 6158
runs/Aug09_20-22-34_61c9bf70029a/events.out.tfevents.1691612587.61c9bf70029a.57273.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388a9efe74a6bd91fa7088247d064eb64c9cb7d5cf999a4bfded2120541b3688
3
+ size 5155
special_tokens_map.json CHANGED
@@ -1,51 +1,107 @@
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
+ "<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
  }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,63 +1,112 @@
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
  "clean_up_tokenization_spaces": true,
12
- "cls_token": {
13
- "__type": "AddedToken",
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "eos_token": {
21
- "__type": "AddedToken",
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
- "errors": "replace",
29
- "mask_token": {
30
- "__type": "AddedToken",
31
- "content": "<mask>",
32
- "lstrip": true,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "model_max_length": 1024,
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
- "tokenizer_class": "BartTokenizer",
55
- "unk_token": {
56
- "__type": "AddedToken",
57
- "content": "<unk>",
58
- "lstrip": false,
59
- "normalized": true,
60
- "rstrip": false,
61
- "single_word": false
62
- }
63
  }
 
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
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
112
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:749aaf2aabecd57d53d78ed3c1caafbb2abda78c505c83800157b763ff5b76a3
3
  size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23432d185cb5a08b969cd496af2a209e85cb36510b17ffca57e5be7f33de2eb
3
  size 3771