Media1129 commited on
Commit
f3209f2
·
1 Parent(s): 65a1dbc
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "ner",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-ingredient",
16
+ "2": "I-ingredient",
17
+ "3": "B-cuisines",
18
+ "4": "I-cuisines",
19
+ "5": "B-mealcourse",
20
+ "6": "I-mealcourse",
21
+ "7": "B-occasion",
22
+ "8": "I-occasion",
23
+ "9": "B-negingredient",
24
+ "10": "I-negingredient"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "O": 0,
30
+ "B-ingredient": 1,
31
+ "I-ingredient": 2,
32
+ "B-cuisines": 3,
33
+ "I-cuisines": 4,
34
+ "B-mealcourse": 5,
35
+ "I-mealcourse": 6,
36
+ "B-occasion": 7,
37
+ "I-occasion": 8,
38
+ "B-negingredient": 9,
39
+ "I-negingredient": 10
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 512,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 12,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.10.2",
50
+ "type_vocab_size": 2,
51
+ "use_cache": true,
52
+ "vocab_size": 30522
53
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d9f8f31ecb2638d4133d0e6a0dc67e4c83d0947a5f377e8ede48f4290a07d0
3
+ size 871325677
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f0751582537acc005c14c729f00e91ef474bd9b56a9506cb93f0f0b0dbcbc0
3
+ size 435688951
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51246b736c44fb50e177d589b4221d11d3b714fc56feabd5aef35e6c20c28ff7
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b689bbd3d2cddbe265555b3681be882e7bb431ab0c9489a28cbe61510b0acc6
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9467878001297858,
5
+ "global_step": 6000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 4.837767683322518e-05,
13
+ "loss": 0.1601,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "learning_rate": 4.6755353666450355e-05,
19
+ "loss": 0.0226,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.49,
24
+ "learning_rate": 4.5133030499675535e-05,
25
+ "loss": 0.0105,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.65,
30
+ "learning_rate": 4.3510707332900715e-05,
31
+ "loss": 0.0054,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.81,
36
+ "learning_rate": 4.1888384166125895e-05,
37
+ "loss": 0.0084,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.97,
42
+ "learning_rate": 4.0266060999351075e-05,
43
+ "loss": 0.0071,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.14,
48
+ "learning_rate": 3.864373783257625e-05,
49
+ "loss": 0.0055,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.3,
54
+ "learning_rate": 3.702141466580143e-05,
55
+ "loss": 0.0024,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.46,
60
+ "learning_rate": 3.539909149902661e-05,
61
+ "loss": 0.0054,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.62,
66
+ "learning_rate": 3.377676833225179e-05,
67
+ "loss": 0.0043,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.78,
72
+ "learning_rate": 3.215444516547697e-05,
73
+ "loss": 0.0065,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.95,
78
+ "learning_rate": 3.053212199870215e-05,
79
+ "loss": 0.0046,
80
+ "step": 6000
81
+ }
82
+ ],
83
+ "max_steps": 15410,
84
+ "num_train_epochs": 5,
85
+ "total_flos": 899535217681332.0,
86
+ "trial_name": null,
87
+ "trial_params": null
88
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ab8435bb882b5a5015f0fffa023605cc64a255c18c7fa9947970060a57ab39
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff