jessietextstan commited on
Commit
63bdcd8
·
1 Parent(s): 2cb5423

End of training

Browse files
Files changed (4) hide show
  1. config.json +20 -58
  2. pytorch_model.bin +2 -2
  3. tokenizer_config.json +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,87 +1,49 @@
1
  {
2
- "_name_or_path": "facebook/bart-base",
3
- "activation_dropout": 0.1,
 
4
  "activation_function": "gelu",
5
- "add_bias_logits": false,
6
  "add_final_layer_norm": false,
7
  "architectures": [
8
  "BartForSequenceClassification"
9
  ],
10
- "attention_dropout": 0.1,
11
  "bos_token_id": 0,
12
- "classif_dropout": 0.1,
13
  "classifier_dropout": 0.0,
14
- "d_model": 768,
15
- "decoder_attention_heads": 12,
16
- "decoder_ffn_dim": 3072,
17
  "decoder_layerdrop": 0.0,
18
- "decoder_layers": 6,
19
  "decoder_start_token_id": 2,
20
  "dropout": 0.1,
21
- "early_stopping": true,
22
- "encoder_attention_heads": 12,
23
- "encoder_ffn_dim": 3072,
24
  "encoder_layerdrop": 0.0,
25
- "encoder_layers": 6,
26
  "eos_token_id": 2,
27
- "forced_bos_token_id": 0,
28
  "forced_eos_token_id": 2,
29
  "gradient_checkpointing": false,
30
  "id2label": {
31
- "0": "fines and fees",
32
- "1": "ARCs or renovations",
33
- "2": "complaints or violations",
34
- "3": "maintenance or service requests",
35
- "4": "pets",
36
- "5": "sale of property",
37
- "6": "property rentals or leasing",
38
- "7": "garbage or trash removal",
39
- "8": "vehicle parking",
40
- "9": "bicycle"
41
  },
42
  "init_std": 0.02,
43
  "is_encoder_decoder": true,
44
  "label2id": {
45
- "9": "bicycle",
46
- "ARCs or renovations": "1",
47
- "complaints or violations": "2",
48
- "fines and fees": "0",
49
- "garbage or trash removal": "7",
50
- "maintenance or service requests": "3",
51
- "pets": "4",
52
- "property rentals or leasing": "6",
53
- "sale of property": "5",
54
- "vehicle parking": "8"
55
  },
56
  "max_position_embeddings": 1024,
57
  "model_type": "bart",
58
- "no_repeat_ngram_size": 3,
59
  "normalize_before": false,
60
- "normalize_embedding": true,
61
- "num_beams": 4,
62
- "num_hidden_layers": 6,
63
  "pad_token_id": 1,
64
  "scale_embedding": false,
65
- "task_specific_params": {
66
- "summarization": {
67
- "length_penalty": 1.0,
68
- "max_length": 128,
69
- "min_length": 12,
70
- "num_beams": 4
71
- },
72
- "summarization_cnn": {
73
- "length_penalty": 2.0,
74
- "max_length": 142,
75
- "min_length": 56,
76
- "num_beams": 4
77
- },
78
- "summarization_xsum": {
79
- "length_penalty": 1.0,
80
- "max_length": 62,
81
- "min_length": 11,
82
- "num_beams": 6
83
- }
84
- },
85
  "torch_dtype": "float32",
86
  "transformers_version": "4.25.1",
87
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "facebook/bart-large-mnli",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
  "activation_function": "gelu",
 
6
  "add_final_layer_norm": false,
7
  "architectures": [
8
  "BartForSequenceClassification"
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
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
 
23
  "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
  "eos_token_id": 2,
 
26
  "forced_eos_token_id": 2,
27
  "gradient_checkpointing": false,
28
  "id2label": {
29
+ "0": "contradiction",
30
+ "1": "neutral",
31
+ "2": "entailment"
 
 
 
 
 
 
 
32
  },
33
  "init_std": 0.02,
34
  "is_encoder_decoder": true,
35
  "label2id": {
36
+ "contradiction": 0,
37
+ "entailment": 2,
38
+ "neutral": 1
 
 
 
 
 
 
 
39
  },
40
  "max_position_embeddings": 1024,
41
  "model_type": "bart",
 
42
  "normalize_before": false,
43
+ "num_hidden_layers": 12,
44
+ "output_past": false,
 
45
  "pad_token_id": 1,
46
  "scale_embedding": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  "torch_dtype": "float32",
48
  "transformers_version": "4.25.1",
49
  "use_cache": true,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c98d6b4281874763908fce4e42792719f95921e391f5795ac533744a1703e1ce
3
- size 560160489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24020715169695c62aed84aa0803f059da8a2284350c6cd5508e83e4df799269
3
+ size 1629544729
tokenizer_config.json CHANGED
@@ -6,7 +6,7 @@
6
  "errors": "replace",
7
  "mask_token": "<mask>",
8
  "model_max_length": 1024,
9
- "name_or_path": "facebook/bart-base",
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
  "special_tokens_map_file": null,
 
6
  "errors": "replace",
7
  "mask_token": "<mask>",
8
  "model_max_length": 1024,
9
+ "name_or_path": "facebook/bart-large-mnli",
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
  "special_tokens_map_file": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a81c18f2e0997cc7fe7f940ace4380ad82e4d7c95ad55f28a1d0646b1cc16ec
3
  size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f8563fef8098dbf43a47d49c1f285ff429a52275cbf64004047580c79940f58
3
  size 3451