amina-mourky commited on
Commit
7fc19f6
·
verified ·
1 Parent(s): 358ba36

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cis-lmu/glot500-base",
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": 0,
15
+ "1": 1,
16
+ "2": 2,
17
+ "3": 3,
18
+ "4": 4,
19
+ "5": 5,
20
+ "6": 6,
21
+ "7": 7,
22
+ "8": 8,
23
+ "9": 9,
24
+ "10": 10,
25
+ "11": 11,
26
+ "12": 12,
27
+ "13": 13,
28
+ "14": 14,
29
+ "15": 15,
30
+ "16": 16,
31
+ "17": 17
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "0": 0,
37
+ "1": 1,
38
+ "2": 2,
39
+ "3": 3,
40
+ "4": 4,
41
+ "5": 5,
42
+ "6": 6,
43
+ "7": 7,
44
+ "8": 8,
45
+ "9": 9,
46
+ "10": 10,
47
+ "11": 11,
48
+ "12": 12,
49
+ "13": 13,
50
+ "14": 14,
51
+ "15": 15,
52
+ "16": 16,
53
+ "17": 17
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "max_position_embeddings": 514,
57
+ "model_type": "xlm-roberta",
58
+ "num_attention_heads": 12,
59
+ "num_hidden_layers": 12,
60
+ "output_past": true,
61
+ "pad_token_id": 1,
62
+ "position_embedding_type": "absolute",
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.48.3",
65
+ "type_vocab_size": 1,
66
+ "use_cache": true,
67
+ "vocab_size": 401145
68
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f49f152d5a15ae8d1304c595e212bcee0882f87ac88eed9eb0ebb5ed7e289c5
3
+ size 1574203208
runs/Feb16_16-21-03_fe604547457b/events.out.tfevents.1739722871.fe604547457b.699.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02899875d32d3625dfb4c76515397cb7caa6d62bbbf672359be41b955c7b69a8
3
+ size 6352
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a313a26470baedaede322622492f2a542aa41527ddc5d40de444e945ad3c613
3
+ size 7658320
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2184548ae8e89465ec16369f7748821608b03c2d7f8953066e00364d8cc77028
3
+ size 26910291
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "401144": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
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": 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 sha256:314bae76562dd4c86766865e24028325f36c6434d359df1ae2acc506bdc42016
3
+ size 5368