dkqjrm commited on
Commit
e092e67
1 Parent(s): 71f8661

Model save

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-cased",
3
+ "adapters": {
4
+ "adapters": {},
5
+ "config_map": {},
6
+ "fusion_config_map": {},
7
+ "fusions": {}
8
+ },
9
+ "architectures": [
10
+ "BertPrefixForSequenceClassification"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "classifier_dropout": null,
14
+ "directionality": "bidi",
15
+ "finetuning_task": "wic",
16
+ "gradient_checkpointing": false,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "id2label": {
21
+ "0": "False",
22
+ "1": "True"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "False": 0,
28
+ "True": 1
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 16,
34
+ "num_hidden_layers": 24,
35
+ "pad_token_id": 0,
36
+ "pooler_fc_size": 768,
37
+ "pooler_num_attention_heads": 12,
38
+ "pooler_num_fc_layers": 3,
39
+ "pooler_size_per_head": 128,
40
+ "pooler_type": "first_token_transform",
41
+ "position_embedding_type": "absolute",
42
+ "pre_seq_len": 1,
43
+ "prefix_hidden_size": 512,
44
+ "prefix_projection": true,
45
+ "problem_type": "single_label_classification",
46
+ "teacher_model_location": "/home/user17/code/COLING/wic_tuning/checkpoints/20230828140242/",
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.26.1",
49
+ "type_vocab_size": 2,
50
+ "use_cache": true,
51
+ "vocab_size": 28996
52
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5fc575cb629e57262deffbd1e85bf7abe2d11b3f17e7c2509607730734bf586
3
+ size 2874879749
runs/Sep03_07-03-06_10-1-16-163/1693692205.735288/events.out.tfevents.1693692205.10-1-16-163.3136277.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c12a9d19d533863d60823747c3a319020715645ae047694c4e6f70025ffc6b
3
+ size 5804
runs/Sep03_07-03-06_10-1-16-163/events.out.tfevents.1693692205.10-1-16-163.3136277.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32c191f00f3f985a85a0757742ee40a89da67914402792de1328eccc17d1b35
3
+ size 53029
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-large-cased",
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f50b2afc83fc4a392aed911eef1c5505a418bb2a2fb56782850c3247e2396a
3
+ size 3579
vocab.txt ADDED
The diff for this file is too large to render. See raw diff