Media1129 commited on
Commit
5e6c808
1 Parent(s): 0385fa4
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "finetuning_task": "ner",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-ingredient",
15
+ "2": "I-ingredient",
16
+ "3": "B-cuisines",
17
+ "4": "I-cuisines",
18
+ "5": "B-mealcourse",
19
+ "6": "I-mealcourse",
20
+ "7": "B-occasion",
21
+ "8": "I-occasion"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "O": 0,
27
+ "B-ingredient": 1,
28
+ "I-ingredient": 2,
29
+ "B-cuisines": 3,
30
+ "I-cuisines": 4,
31
+ "B-mealcourse": 5,
32
+ "I-mealcourse": 6,
33
+ "B-occasion": 7,
34
+ "I-occasion": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.9.1",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe83c26ae76d5d93e1957215fb0179310660f1ebaa579ad6c4fc38211140e10
3
+ size 871313389
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18cb2c391a81bf1fefe1e3674b5d61d4cccf3981c080a91e1f96fd993adbe89
3
+ size 435682807
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb839d52116fc81521e1cce677654e57def16b6ad2e9658db7953a663daf0fa
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86f1b35e573bdf2990c3537ab12b9cbd7afe67dc47eb0291e8daad0a519dc09
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": 2.1881838074398248,
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": 0.18,
12
+ "learning_rate": 4.817651349380015e-05,
13
+ "loss": 0.1396,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 4.6353026987600294e-05,
19
+ "loss": 0.0182,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.55,
24
+ "learning_rate": 4.452954048140044e-05,
25
+ "loss": 0.0148,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.73,
30
+ "learning_rate": 4.2706053975200585e-05,
31
+ "loss": 0.009,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.91,
36
+ "learning_rate": 4.088256746900073e-05,
37
+ "loss": 0.0083,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.09,
42
+ "learning_rate": 3.9059080962800876e-05,
43
+ "loss": 0.0072,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.28,
48
+ "learning_rate": 3.723559445660103e-05,
49
+ "loss": 0.004,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.46,
54
+ "learning_rate": 3.541210795040117e-05,
55
+ "loss": 0.0052,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.64,
60
+ "learning_rate": 3.358862144420131e-05,
61
+ "loss": 0.0032,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.82,
66
+ "learning_rate": 3.1765134938001465e-05,
67
+ "loss": 0.0029,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.01,
72
+ "learning_rate": 2.9941648431801604e-05,
73
+ "loss": 0.0055,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.19,
78
+ "learning_rate": 2.811816192560175e-05,
79
+ "loss": 0.0027,
80
+ "step": 6000
81
+ }
82
+ ],
83
+ "max_steps": 13710,
84
+ "num_train_epochs": 5,
85
+ "total_flos": 913869748994976.0,
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:b91b3084725beeceaf4b2ad6b0a9decb7422bdd9a1ba4e3eecc94316284beb94
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff