ultra-coder54732 commited on
Commit
53c2d5c
·
1 Parent(s): ff3bb2c

End of training

Browse files
config.json CHANGED
@@ -1,19 +1,14 @@
1
  {
2
- "_name_or_path": "xlnet-base-cased",
3
  "architectures": [
4
- "XLNetForSequenceClassification"
5
  ],
6
- "attn_type": "bi",
7
- "bi_data": false,
8
- "bos_token_id": 1,
9
- "clamp_len": -1,
10
- "d_head": 64,
11
- "d_inner": 3072,
12
- "d_model": 768,
13
- "dropout": 0.1,
14
- "end_n_top": 5,
15
- "eos_token_id": 2,
16
- "ff_activation": "gelu",
17
  "id2label": {
18
  "0": "LABEL_0",
19
  "1": "LABEL_1",
@@ -21,6 +16,7 @@
21
  "3": "LABEL_3"
22
  },
23
  "initializer_range": 0.02,
 
24
  "label2id": {
25
  "LABEL_0": 0,
26
  "LABEL_1": 1,
@@ -28,29 +24,16 @@
28
  "LABEL_3": 3
29
  },
30
  "layer_norm_eps": 1e-12,
31
- "mem_len": null,
32
- "model_type": "xlnet",
33
- "n_head": 12,
34
- "n_layer": 12,
35
- "pad_token_id": 5,
 
36
  "problem_type": "single_label_classification",
37
- "reuse_len": null,
38
- "same_length": false,
39
- "start_n_top": 5,
40
- "summary_activation": "tanh",
41
- "summary_last_dropout": 0.1,
42
- "summary_type": "last",
43
- "summary_use_proj": true,
44
- "task_specific_params": {
45
- "text-generation": {
46
- "do_sample": true,
47
- "max_length": 250
48
- }
49
- },
50
  "torch_dtype": "float32",
51
  "transformers_version": "4.21.1",
52
- "untie_r": true,
53
- "use_mems_eval": true,
54
- "use_mems_train": false,
55
- "vocab_size": 32000
56
  }
 
1
  {
2
+ "_name_or_path": "ultra-coder54732/4-way-detection-prop-16-bert",
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
 
 
 
 
 
12
  "id2label": {
13
  "0": "LABEL_0",
14
  "1": "LABEL_1",
 
16
  "3": "LABEL_3"
17
  },
18
  "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
 
24
  "LABEL_3": 3
25
  },
26
  "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.21.1",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30522
 
39
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb1751ca96f224c9ad5fc4f2d7ecfc53aeb64da2a0ae8afd85d2e46433116c52
3
- size 469315997
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc7e934319972af614319f778696f931ded54cf3d5416bba3bf1e156941349d
3
+ size 438012269
special_tokens_map.json CHANGED
@@ -1,19 +1,7 @@
1
  {
2
- "additional_special_tokens": [
3
- "<eop>",
4
- "<eod>"
5
- ],
6
- "bos_token": "<s>",
7
- "cls_token": "<cls>",
8
- "eos_token": "</s>",
9
- "mask_token": {
10
- "content": "<mask>",
11
- "lstrip": true,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<pad>",
17
- "sep_token": "<sep>",
18
- "unk_token": "<unk>"
19
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,26 +1,14 @@
1
  {
2
- "additional_special_tokens": [
3
- "<eop>",
4
- "<eod>"
5
- ],
6
- "bos_token": "<s>",
7
- "cls_token": "<cls>",
8
- "do_lower_case": false,
9
- "eos_token": "</s>",
10
- "keep_accents": false,
11
- "mask_token": {
12
- "__type": "AddedToken",
13
- "content": "<mask>",
14
- "lstrip": true,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "name_or_path": "xlnet-base-cased",
20
- "pad_token": "<pad>",
21
- "remove_space": true,
22
- "sep_token": "<sep>",
23
  "special_tokens_map_file": null,
24
- "tokenizer_class": "XLNetTokenizer",
25
- "unk_token": "<unk>"
 
 
26
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "ultra-coder54732/4-way-detection-prop-16-bert",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4de97ab0066d62072e9d084f1f809a9a92b7651eea806e9b218d14f11cdf4ff5
3
  size 3375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1910950ab7d1ebe249cc447ef265308f673bb57deefcce2c45b1ee74b986eda1
3
  size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff