ndamulelonemakh commited on
Commit
16fb52f
1 Parent(s): 9e2185c

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dsfsi/zabantu-ven-120m",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-ADJ",
15
+ "1": "B-ADP",
16
+ "2": "B-ADV",
17
+ "3": "B-AUX",
18
+ "4": "B-CCONJ",
19
+ "5": "B-DET",
20
+ "6": "B-INTJ",
21
+ "7": "B-NOUN",
22
+ "8": "B-NUM",
23
+ "9": "B-PART",
24
+ "10": "B-PREP",
25
+ "11": "B-PRON",
26
+ "12": "B-PROPN",
27
+ "13": "B-PUNCT",
28
+ "14": "B-SCONJ",
29
+ "15": "B-SYM",
30
+ "16": "B-VERB",
31
+ "17": "I-ADJ",
32
+ "18": "I-ADV",
33
+ "19": "I-NOUN",
34
+ "20": "I-PREP",
35
+ "21": "I-VERB",
36
+ "22": "OUT"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "label2id": {
41
+ "B-ADJ": 0,
42
+ "B-ADP": 1,
43
+ "B-ADV": 2,
44
+ "B-AUX": 3,
45
+ "B-CCONJ": 4,
46
+ "B-DET": 5,
47
+ "B-INTJ": 6,
48
+ "B-NOUN": 7,
49
+ "B-NUM": 8,
50
+ "B-PART": 9,
51
+ "B-PREP": 10,
52
+ "B-PRON": 11,
53
+ "B-PROPN": 12,
54
+ "B-PUNCT": 13,
55
+ "B-SCONJ": 14,
56
+ "B-SYM": 15,
57
+ "B-VERB": 16,
58
+ "I-ADJ": 17,
59
+ "I-ADV": 18,
60
+ "I-NOUN": 19,
61
+ "I-PREP": 20,
62
+ "I-VERB": 21,
63
+ "OUT": 22
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "max_length": 512,
67
+ "max_position_embeddings": 514,
68
+ "model_type": "xlm-roberta",
69
+ "num_attention_heads": 6,
70
+ "num_hidden_layers": 8,
71
+ "output_past": true,
72
+ "pad_token_id": 1,
73
+ "position_embedding_type": "absolute",
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.41.2",
76
+ "type_vocab_size": 1,
77
+ "use_cache": true,
78
+ "vocab_size": 85002
79
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e8c23d817a99f9bff166f07595a9397f1e553e757d671e6152d95b9374d387
3
+ size 489613196
runs/Jun12_23-19-56_5a020c0f2fe4/events.out.tfevents.1718234399.5a020c0f2fe4.19326.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cd2c805595389ee6dc608a9e4374a69951c2dc9f77b25d7e79c59fbe216033
3
+ size 7353
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b466433a20fff054cffaa0ad5d6ef590c92f49f0b377e90822502390b62ef0e
3
+ size 1697529
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": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "85001": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>",
56
+ "use_fast": true
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718070cf4bfbfe03375937b37a921e46263f167a0a7a0d5dd6fa162441628890
3
+ size 5176