sagorbrur commited on
Commit
f17cb95
1 Parent(s): 6973c70

model added

Browse files
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
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",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5,
30
+ "LABEL_6": 6
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "pooler_fc_size": 768,
39
+ "pooler_num_attention_heads": 12,
40
+ "pooler_num_fc_layers": 3,
41
+ "pooler_size_per_head": 128,
42
+ "pooler_type": "first_token_transform",
43
+ "position_embedding_type": "absolute",
44
+ "transformers_version": "4.6.1",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 105879
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5cdcbd9be9bf03764936528c700daee3b1d49c523c27c5d86dc484591e27f6
3
+ size 667173367
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-multilingual-uncased"}
trainer_state.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.8,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.8,
12
+ "learning_rate": 1.6800000000000002e-05,
13
+ "loss": 0.5178,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.946119307248236,
19
+ "eval_f1": 0.9269931515699703,
20
+ "eval_loss": 0.20892712473869324,
21
+ "eval_precision": 0.9278323848939473,
22
+ "eval_recall": 0.9261554350632585,
23
+ "eval_runtime": 2.7187,
24
+ "eval_samples_per_second": 367.826,
25
+ "step": 625
26
+ },
27
+ {
28
+ "epoch": 1.6,
29
+ "learning_rate": 1.3600000000000002e-05,
30
+ "loss": 0.2064,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.9685695958948044,
36
+ "eval_f1": 0.9600723607701254,
37
+ "eval_loss": 0.1718911975622177,
38
+ "eval_precision": 0.9609415416451113,
39
+ "eval_recall": 0.9592047508391428,
40
+ "eval_runtime": 2.6825,
41
+ "eval_samples_per_second": 372.791,
42
+ "step": 1250
43
+ },
44
+ {
45
+ "epoch": 2.4,
46
+ "learning_rate": 1.04e-05,
47
+ "loss": 0.1378,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.9693713919178961,
53
+ "eval_f1": 0.961869302863012,
54
+ "eval_loss": 0.16582955420017242,
55
+ "eval_precision": 0.95658835546476,
56
+ "eval_recall": 0.9672088820036148,
57
+ "eval_runtime": 2.6697,
58
+ "eval_samples_per_second": 374.576,
59
+ "step": 1875
60
+ },
61
+ {
62
+ "epoch": 3.2,
63
+ "learning_rate": 7.2000000000000005e-06,
64
+ "loss": 0.0884,
65
+ "step": 2000
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "learning_rate": 4.000000000000001e-06,
70
+ "loss": 0.0616,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.9757857601026299,
76
+ "eval_f1": 0.9698453608247423,
77
+ "eval_loss": 0.1476062387228012,
78
+ "eval_precision": 0.9680987908412657,
79
+ "eval_recall": 0.9715982442550994,
80
+ "eval_runtime": 4.3214,
81
+ "eval_samples_per_second": 231.405,
82
+ "step": 2500
83
+ },
84
+ {
85
+ "epoch": 4.8,
86
+ "learning_rate": 8.000000000000001e-07,
87
+ "loss": 0.0426,
88
+ "step": 3000
89
+ }
90
+ ],
91
+ "max_steps": 3125,
92
+ "num_train_epochs": 5,
93
+ "total_flos": 228175031247744.0,
94
+ "trial_name": null,
95
+ "trial_params": null
96
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e067d6e545a7da36bbbb792e004d1b4d68eac0bc82cc3bb3be58fe8e589dce65
3
+ size 2415
vocab.txt ADDED
The diff for this file is too large to render. See raw diff