ndamulelonemakh
commited on
Commit
•
0653c74
1
Parent(s):
cdc754c
Training in progress, epoch 1
Browse files- config.json +61 -0
- model.safetensors +3 -0
- runs/Jun12_21-59-37_71746c4e-2387-4465-b684-f00ad02044b8/events.out.tfevents.1718229615.71746c4e-2387-4465-b684-f00ad02044b8.4750.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-DATE",
|
15 |
+
"1": "B-LOC",
|
16 |
+
"2": "B-MISC",
|
17 |
+
"3": "B-ORG",
|
18 |
+
"4": "B-PER",
|
19 |
+
"5": "B-PERS",
|
20 |
+
"6": "I-DATE",
|
21 |
+
"7": "I-LOC",
|
22 |
+
"8": "I-MISC",
|
23 |
+
"9": "I-ORG",
|
24 |
+
"10": "I-PER",
|
25 |
+
"11": "I-PERS",
|
26 |
+
"12": "O",
|
27 |
+
"13": "OUT"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"B-DATE": 0,
|
33 |
+
"B-LOC": 1,
|
34 |
+
"B-MISC": 2,
|
35 |
+
"B-ORG": 3,
|
36 |
+
"B-PER": 4,
|
37 |
+
"B-PERS": 5,
|
38 |
+
"I-DATE": 6,
|
39 |
+
"I-LOC": 7,
|
40 |
+
"I-MISC": 8,
|
41 |
+
"I-ORG": 9,
|
42 |
+
"I-PER": 10,
|
43 |
+
"I-PERS": 11,
|
44 |
+
"O": 12,
|
45 |
+
"OUT": 13
|
46 |
+
},
|
47 |
+
"layer_norm_eps": 1e-05,
|
48 |
+
"max_length": 512,
|
49 |
+
"max_position_embeddings": 514,
|
50 |
+
"model_type": "xlm-roberta",
|
51 |
+
"num_attention_heads": 6,
|
52 |
+
"num_hidden_layers": 8,
|
53 |
+
"output_past": true,
|
54 |
+
"pad_token_id": 1,
|
55 |
+
"position_embedding_type": "absolute",
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.41.2",
|
58 |
+
"type_vocab_size": 1,
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 85002
|
61 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687eb604a3bb8a6c2946f1087535195fc8209c80696b570c91773fc7487c8df9
|
3 |
+
size 489585512
|
runs/Jun12_21-59-37_71746c4e-2387-4465-b684-f00ad02044b8/events.out.tfevents.1718229615.71746c4e-2387-4465-b684-f00ad02044b8.4750.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cb9ecf0a002ad3538b96bbcd371850b89427a79eb9342b3a5f49f086f4967fa
|
3 |
+
size 7126
|
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:f72ad542fda628d6f94404084e3b94f2767988983404d949e5da9198cfd4956f
|
3 |
+
size 5304
|