softhell commited on
Commit
e70b1bd
·
verified ·
1 Parent(s): e68bf49

codet5_train_2

Browse files
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  library_name: transformers
3
- base_model: uclanlp/plbart-base
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -22,7 +23,7 @@ model-index:
22
  metrics:
23
  - name: Bleu
24
  type: bleu
25
- value: 0.0
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # code_docstring_model
32
 
33
- This model is a fine-tuned version of [uclanlp/plbart-base](https://huggingface.co/uclanlp/plbart-base) on the code_search_net dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.8020
36
- - Bleu: 0.0
37
 
38
  ## Model description
39
 
@@ -60,18 +61,33 @@ The following hyperparameters were used during training:
60
  - total_train_batch_size: 32
61
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: linear
63
- - num_epochs: 5
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Bleu |
69
- |:-------------:|:------:|:----:|:---------------:|:----:|
70
- | 0.8912 | 0.9993 | 1076 | 0.8366 | 0.0 |
71
- | 0.7932 | 1.9993 | 2152 | 0.8140 | 0.0 |
72
- | 0.7662 | 2.9993 | 3228 | 0.8060 | 0.0 |
73
- | 0.7433 | 3.9993 | 4304 | 0.8027 | 0.0 |
74
- | 0.7351 | 4.9993 | 5380 | 0.8020 | 0.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Salesforce/codet5-small
5
  tags:
6
  - generated_from_trainer
7
  datasets:
 
23
  metrics:
24
  - name: Bleu
25
  type: bleu
26
+ value: 0.08377962983846503
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # code_docstring_model
33
 
34
+ This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on the code_search_net dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.9435
37
+ - Bleu: 0.0838
38
 
39
  ## Model description
40
 
 
61
  - total_train_batch_size: 32
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
+ - num_epochs: 20
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Bleu |
70
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
71
+ | 1.2873 | 0.9993 | 1076 | 1.1220 | 0.2248 |
72
+ | 1.1474 | 1.9993 | 2152 | 1.0673 | 0.2589 |
73
+ | 1.112 | 2.9993 | 3228 | 1.0406 | 0.2379 |
74
+ | 1.0849 | 3.9993 | 4304 | 1.0252 | 0.2432 |
75
+ | 1.0602 | 4.9993 | 5380 | 1.0126 | 0.1499 |
76
+ | 1.0565 | 5.9993 | 6456 | 1.0030 | 0.1413 |
77
+ | 1.0576 | 6.9993 | 7532 | 0.9964 | 0.0616 |
78
+ | 1.0174 | 7.9993 | 8608 | 0.9883 | 0.0935 |
79
+ | 1.0301 | 8.9993 | 9684 | 0.9828 | 0.0843 |
80
+ | 0.9884 | 9.9993 | 10760 | 0.9768 | 0.1363 |
81
+ | 0.9998 | 10.9993 | 11836 | 0.9702 | 0.1104 |
82
+ | 0.995 | 11.9993 | 12912 | 0.9647 | 0.1169 |
83
+ | 0.9852 | 12.9993 | 13988 | 0.9593 | 0.0962 |
84
+ | 0.9594 | 13.9993 | 15064 | 0.9549 | 0.0973 |
85
+ | 0.9553 | 14.9993 | 16140 | 0.9510 | 0.0923 |
86
+ | 0.9717 | 15.9993 | 17216 | 0.9486 | 0.0821 |
87
+ | 0.9667 | 16.9993 | 18292 | 0.9468 | 0.0888 |
88
+ | 0.957 | 17.9993 | 19368 | 0.9448 | 0.0858 |
89
+ | 0.9649 | 18.9993 | 20444 | 0.9438 | 0.0875 |
90
+ | 0.9454 | 19.9993 | 21520 | 0.9435 | 0.0838 |
91
 
92
 
93
  ### Framework versions
added_tokens.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "Args:": 50005,
3
- "Examples:": 50008,
4
- "Raises:": 50007,
5
- "Returns:": 50006
6
  }
 
1
  {
2
+ "Args:": 32100,
3
+ "Examples:": 32103,
4
+ "Raises:": 32102,
5
+ "Returns:": 32101
6
  }
config.json CHANGED
@@ -1,34 +1,69 @@
1
  {
2
- "_name_or_path": "uclanlp/plbart-base",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
  "architectures": [
6
- "PLBartForConditionalGeneration"
7
  ],
8
- "attention_dropout": 0.1,
9
- "bos_token_id": 0,
10
  "classifier_dropout": 0.0,
11
- "d_model": 768,
12
- "decoder_attention_heads": 12,
13
- "decoder_ffn_dim": 3072,
14
- "decoder_layerdrop": 0.0,
15
- "decoder_layers": 6,
16
- "dropout": 0.1,
17
- "encoder_attention_heads": 12,
18
- "encoder_ffn_dim": 3072,
19
- "encoder_layerdrop": 0.0,
20
- "encoder_layers": 6,
21
  "eos_token_id": 2,
22
- "forced_eos_token_id": 2,
23
- "init_std": 0.02,
 
 
 
 
24
  "is_encoder_decoder": true,
25
- "max_position_embeddings": 1024,
26
- "model_type": "plbart",
27
- "num_hidden_layers": 6,
28
- "pad_token_id": 1,
29
- "scale_embedding": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.47.0",
32
  "use_cache": true,
33
- "vocab_size": 50009
34
  }
 
1
  {
2
+ "_name_or_path": "Salesforce/codet5-small",
 
 
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
6
+ "bos_token_id": 1,
 
7
  "classifier_dropout": 0.0,
8
+ "d_ff": 2048,
9
+ "d_kv": 64,
10
+ "d_model": 512,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
 
 
 
 
14
  "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
  "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "model_type": "t5",
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 6,
30
+ "num_heads": 8,
31
+ "num_layers": 6,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "relative_attention_max_distance": 128,
35
+ "relative_attention_num_buckets": 32,
36
+ "task_specific_params": {
37
+ "summarization": {
38
+ "early_stopping": true,
39
+ "length_penalty": 2.0,
40
+ "max_length": 200,
41
+ "min_length": 30,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 4,
44
+ "prefix": "summarize: "
45
+ },
46
+ "translation_en_to_de": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to German: "
51
+ },
52
+ "translation_en_to_fr": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to French: "
57
+ },
58
+ "translation_en_to_ro": {
59
+ "early_stopping": true,
60
+ "max_length": 300,
61
+ "num_beams": 4,
62
+ "prefix": "translate English to Romanian: "
63
+ }
64
+ },
65
  "torch_dtype": "float32",
66
  "transformers_version": "4.47.0",
67
  "use_cache": true,
68
+ "vocab_size": 32104
69
  }
generation_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "bos_token_id": 0,
 
3
  "eos_token_id": 2,
4
- "forced_eos_token_id": 2,
5
- "pad_token_id": 1,
6
  "transformers_version": "4.47.0"
7
  }
 
1
  {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
  "eos_token_id": 2,
5
+ "pad_token_id": 0,
 
6
  "transformers_version": "4.47.0"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:389b4db9524e8785c641e5271747f01c28474cad73e31ba24f5af8a2531cd150
3
- size 557125164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139c4cfde4ed2c2ae9f4c2888db34288d73de0e738f4796f12e13207547f3236
3
+ size 241992744
special_tokens_map.json CHANGED
@@ -29,9 +29,27 @@
29
  "single_word": false
30
  }
31
  ],
32
- "bos_token": "<s>",
33
- "cls_token": "<s>",
34
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "mask_token": {
36
  "content": "<mask>",
37
  "lstrip": true,
@@ -39,7 +57,25 @@
39
  "rstrip": false,
40
  "single_word": false
41
  },
42
- "pad_token": "<pad>",
43
- "sep_token": "</s>",
44
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  }
 
29
  "single_word": false
30
  }
31
  ],
32
+ "bos_token": {
33
+ "content": "<s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "cls_token": {
40
+ "content": "<s>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
  "mask_token": {
54
  "content": "<mask>",
55
  "lstrip": true,
 
57
  "rstrip": false,
58
  "single_word": false
59
  },
60
+ "pad_token": {
61
+ "content": "<pad>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "sep_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "unk_token": {
75
+ "content": "<unk>",
76
+ "lstrip": false,
77
+ "normalized": true,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ }
81
  }
tokenizer_config.json CHANGED
@@ -1,17 +1,18 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<s>",
5
  "lstrip": false,
6
- "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<pad>",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,7 +20,7 @@
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
@@ -27,44 +28,820 @@
27
  "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
- "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "50001": {
36
- "content": "__java__",
37
- "lstrip": false,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  },
43
- "50002": {
44
- "content": "__python__",
45
- "lstrip": false,
46
- "normalized": false,
47
  "rstrip": false,
48
  "single_word": false,
49
  "special": true
50
  },
51
- "50003": {
52
- "content": "__en_XX__",
53
- "lstrip": false,
54
- "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
  },
59
- "50004": {
60
- "content": "<mask>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  "lstrip": true,
62
  "normalized": true,
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
66
  },
67
- "50005": {
68
  "content": "Args:",
69
  "lstrip": false,
70
  "normalized": false,
@@ -72,7 +849,7 @@
72
  "single_word": false,
73
  "special": true
74
  },
75
- "50006": {
76
  "content": "Returns:",
77
  "lstrip": false,
78
  "normalized": false,
@@ -80,7 +857,7 @@
80
  "single_word": false,
81
  "special": true
82
  },
83
- "50007": {
84
  "content": "Raises:",
85
  "lstrip": false,
86
  "normalized": false,
@@ -88,7 +865,7 @@
88
  "single_word": false,
89
  "special": true
90
  },
91
- "50008": {
92
  "content": "Examples:",
93
  "lstrip": false,
94
  "normalized": false,
@@ -104,18 +881,16 @@
104
  "Examples:"
105
  ],
106
  "bos_token": "<s>",
107
- "clean_up_tokenization_spaces": true,
108
  "cls_token": "<s>",
109
  "eos_token": "</s>",
 
110
  "extra_special_tokens": {},
111
- "language_codes": "base",
112
  "mask_token": "<mask>",
113
- "model_max_length": 1000000000000000019884624838656,
114
  "pad_token": "<pad>",
115
  "sep_token": "</s>",
116
- "sp_model_kwargs": {},
117
- "src_lang": null,
118
- "tgt_lang": null,
119
- "tokenizer_class": "PLBartTokenizer",
120
  "unk_token": "<unk>"
121
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<pad>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
  "1": {
13
+ "content": "<s>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
  "rstrip": false,
49
  "single_word": false,
50
  "special": true
51
  },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
  "rstrip": false,
57
  "single_word": false,
58
  "special": true
59
  },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
  "lstrip": true,
839
  "normalized": true,
840
  "rstrip": false,
841
  "single_word": false,
842
  "special": true
843
  },
844
+ "32100": {
845
  "content": "Args:",
846
  "lstrip": false,
847
  "normalized": false,
 
849
  "single_word": false,
850
  "special": true
851
  },
852
+ "32101": {
853
  "content": "Returns:",
854
  "lstrip": false,
855
  "normalized": false,
 
857
  "single_word": false,
858
  "special": true
859
  },
860
+ "32102": {
861
  "content": "Raises:",
862
  "lstrip": false,
863
  "normalized": false,
 
865
  "single_word": false,
866
  "special": true
867
  },
868
+ "32103": {
869
  "content": "Examples:",
870
  "lstrip": false,
871
  "normalized": false,
 
881
  "Examples:"
882
  ],
883
  "bos_token": "<s>",
884
+ "clean_up_tokenization_spaces": false,
885
  "cls_token": "<s>",
886
  "eos_token": "</s>",
887
+ "errors": "replace",
888
  "extra_special_tokens": {},
 
889
  "mask_token": "<mask>",
890
+ "model_max_length": 512,
891
  "pad_token": "<pad>",
892
  "sep_token": "</s>",
893
+ "tokenizer_class": "RobertaTokenizer",
894
+ "trim_offsets": true,
 
 
895
  "unk_token": "<unk>"
896
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3947da51dfe822b2bcdcf390e3b14c28c1425dc937be98bbd3e8c141a88fc65c
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef2df3496087df5e39737165b6368e1e8c1ada498e92b93d63343e96ccc4ce8
3
  size 5496