Hugging Face's logo

languageDocumentation
/
bam_postagger

Safetensors
xlm-roberta
Model card Files
xet
 Community
minaolenpavel commited on
Commit
f792007
·
verified ·
1 Parent(s): 0d30bd8

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +77 -0
  2. id2tag.json +24 -0
  3. logs.txt +77 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +15 -0
  6. tag2id.json +24 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +56 -0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8",
24
+ "9": "LABEL_9",
25
+ "10": "LABEL_10",
26
+ "11": "LABEL_11",
27
+ "12": "LABEL_12",
28
+ "13": "LABEL_13",
29
+ "14": "LABEL_14",
30
+ "15": "LABEL_15",
31
+ "16": "LABEL_16",
32
+ "17": "LABEL_17",
33
+ "18": "LABEL_18",
34
+ "19": "LABEL_19",
35
+ "20": "LABEL_20",
36
+ "21": "LABEL_21"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_10": 10,
44
+ "LABEL_11": 11,
45
+ "LABEL_12": 12,
46
+ "LABEL_13": 13,
47
+ "LABEL_14": 14,
48
+ "LABEL_15": 15,
49
+ "LABEL_16": 16,
50
+ "LABEL_17": 17,
51
+ "LABEL_18": 18,
52
+ "LABEL_19": 19,
53
+ "LABEL_2": 2,
54
+ "LABEL_20": 20,
55
+ "LABEL_21": 21,
56
+ "LABEL_3": 3,
57
+ "LABEL_4": 4,
58
+ "LABEL_5": 5,
59
+ "LABEL_6": 6,
60
+ "LABEL_7": 7,
61
+ "LABEL_8": 8,
62
+ "LABEL_9": 9
63
+ },
64
+ "layer_norm_eps": 1e-05,
65
+ "max_length": 512,
66
+ "max_position_embeddings": 514,
67
+ "model_type": "xlm-roberta",
68
+ "num_attention_heads": 6,
69
+ "num_hidden_layers": 8,
70
+ "output_past": true,
71
+ "pad_token_id": 1,
72
+ "position_embedding_type": "absolute",
73
+ "transformers_version": "4.57.6",
74
+ "type_vocab_size": 1,
75
+ "use_cache": true,
76
+ "vocab_size": 70006
77
+ }
id2tag.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": "adj",
3
+ "1": "adv",
4
+ "2": "adv.p",
5
+ "3": "conj",
6
+ "4": "conv.n",
7
+ "5": "cop",
8
+ "6": "dtm",
9
+ "7": "intj",
10
+ "8": "mrph",
11
+ "9": "n",
12
+ "10": "n.prop",
13
+ "11": "num",
14
+ "12": "onomat",
15
+ "13": "pers",
16
+ "14": "pm",
17
+ "15": "pp",
18
+ "16": "prep",
19
+ "17": "prn",
20
+ "18": "prt",
21
+ "19": "ptcp",
22
+ "20": "v",
23
+ "21": "vq"
24
+ }
logs.txt ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ==================================================
2
+ Training config
3
+ ==================================================
4
+ Model name : castorini/afriberta_base
5
+ Tokenizer name : castorini/afriberta_base
6
+ Number of labels : 22
7
+ Batch size : 8
8
+ Learning rate : 5e-05
9
+ Number of epochs : 16
10
+ Random seed : 42
11
+
12
+ ==================================================
13
+ Epoch 1
14
+ ==================================================
15
+ Traning loss : 818.2853
16
+ Validation loss : 0.1867
17
+ Precision : 0.8856
18
+ Recall : 0.8025
19
+ F1-score : 0.8285
20
+ Checkpoint saved
21
+
22
+ ==================================================
23
+ Epoch 2
24
+ ==================================================
25
+ Traning loss : 245.6919
26
+ Validation loss : 0.1653
27
+ Precision : 0.9115
28
+ Recall : 0.7915
29
+ F1-score : 0.8174
30
+
31
+ ==================================================
32
+ Epoch 3
33
+ ==================================================
34
+ Traning loss : 124.5959
35
+ Validation loss : 0.1279
36
+ Precision : 0.9503
37
+ Recall : 0.8683
38
+ F1-score : 0.8944
39
+ Checkpoint saved
40
+
41
+ ==================================================
42
+ Epoch 4
43
+ ==================================================
44
+ Traning loss : 76.5310
45
+ Validation loss : 0.2006
46
+ Precision : 0.9543
47
+ Recall : 0.8714
48
+ F1-score : 0.8966
49
+ Checkpoint saved
50
+
51
+ ==================================================
52
+ Epoch 5
53
+ ==================================================
54
+ Traning loss : 55.0676
55
+ Validation loss : 0.1981
56
+ Precision : 0.9374
57
+ Recall : 0.8800
58
+ F1-score : 0.8927
59
+
60
+ ==================================================
61
+ Epoch 6
62
+ ==================================================
63
+ Traning loss : 36.3393
64
+ Validation loss : 0.1937
65
+ Precision : 0.9037
66
+ Recall : 0.8220
67
+ F1-score : 0.8429
68
+
69
+ ==================================================
70
+ Epoch 7
71
+ ==================================================
72
+ Traning loss : 21.6568
73
+ Validation loss : 0.1819
74
+ Precision : 0.8993
75
+ Recall : 0.8509
76
+ F1-score : 0.8652
77
+ Early stopping triggered
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88ecd305a8bf0e644b4d05dd22a32591e9304f3a149afdd345abfe3d4c92ebe
3
+ size 443542408
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tag2id.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adj": 0,
3
+ "adv": 1,
4
+ "adv.p": 2,
5
+ "conj": 3,
6
+ "conv.n": 4,
7
+ "cop": 5,
8
+ "dtm": 6,
9
+ "intj": 7,
10
+ "mrph": 8,
11
+ "n": 9,
12
+ "n.prop": 10,
13
+ "num": 11,
14
+ "onomat": 12,
15
+ "pers": 13,
16
+ "pm": 14,
17
+ "pp": 15,
18
+ "prep": 16,
19
+ "prn": 17,
20
+ "prt": 18,
21
+ "ptcp": 19,
22
+ "v": 20,
23
+ "vq": 21
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "70005": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }