balhafni commited on
Commit
c5e027f
1 Parent(s): e665dae

Uploading model

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/ba63/BERT_models/bert-base-arabic-camelbert-msa",
3
+ "architectures": [
4
+ "BertForTokenClassificationSingleLabel"
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": "DELETE",
14
+ "1": "MERGE-B",
15
+ "2": "MERGE-I",
16
+ "3": "REPLACE_M",
17
+ "4": "REPLACE_M+REPLACE_O",
18
+ "5": "REPLACE_O",
19
+ "6": "REPLACE_O+REPLACE_X",
20
+ "7": "REPLACE_P",
21
+ "8": "REPLACE_S",
22
+ "9": "REPLACE_X",
23
+ "10": "SPLIT",
24
+ "11": "UC"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "DELETE": 0,
30
+ "MERGE-B": 1,
31
+ "MERGE-I": 2,
32
+ "REPLACE_M": 3,
33
+ "REPLACE_M+REPLACE_O": 4,
34
+ "REPLACE_O": 5,
35
+ "REPLACE_O+REPLACE_X": 6,
36
+ "REPLACE_P": 7,
37
+ "REPLACE_S": 8,
38
+ "REPLACE_X": 9,
39
+ "SPLIT": 10,
40
+ "UC": 11
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "max_position_embeddings": 512,
44
+ "model_type": "bert",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 0,
48
+ "position_embedding_type": "absolute",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.22.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 30000
54
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f47d95093ef13faf62ad0f855b2ba91655f8f8b44bf01bbd29b9a1d47b2a90
3
+ size 434070321
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_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "full_tokenizer_file": null,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "name_or_path": "/scratch/ba63/BERT_models/bert-base-arabic-camelbert-msa",
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "special_tokens_map_file": null,
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
trainer_state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.724473257698541,
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": 0.81,
12
+ "learning_rate": 4.594813614262561e-05,
13
+ "loss": 0.2452,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.62,
18
+ "learning_rate": 4.189627228525122e-05,
19
+ "loss": 0.1664,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.43,
24
+ "learning_rate": 3.7844408427876825e-05,
25
+ "loss": 0.1397,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.24,
30
+ "learning_rate": 3.379254457050243e-05,
31
+ "loss": 0.1179,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 4.05,
36
+ "learning_rate": 2.974068071312804e-05,
37
+ "loss": 0.0962,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 4.86,
42
+ "learning_rate": 2.568881685575365e-05,
43
+ "loss": 0.0743,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 5.67,
48
+ "learning_rate": 2.1636952998379258e-05,
49
+ "loss": 0.0589,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 6.48,
54
+ "learning_rate": 1.7585089141004862e-05,
55
+ "loss": 0.0486,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 7.29,
60
+ "learning_rate": 1.3533225283630471e-05,
61
+ "loss": 0.0398,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 8.1,
66
+ "learning_rate": 9.481361426256078e-06,
67
+ "loss": 0.0327,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 8.91,
72
+ "learning_rate": 5.429497568881686e-06,
73
+ "loss": 0.0268,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 9.72,
78
+ "learning_rate": 1.3776337115072935e-06,
79
+ "loss": 0.0236,
80
+ "step": 6000
81
+ }
82
+ ],
83
+ "max_steps": 6170,
84
+ "num_train_epochs": 10,
85
+ "total_flos": 1.3626404244078336e+16,
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 sha256:8969534c4440f75c9ad24d508d71e98ccfd160cfa0d675cc1bca0680e0047263
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff