seanghay commited on
Commit
ea55206
1 Parent(s): f5fb892

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": "\u1780\u17b8\u17a1\u17b6\u1787\u17b6\u178f\u17b7",
15
+ "1": "\u1780\u17b8\u17a1\u17b6\u17a2\u1793\u17d2\u178f\u179a\u1787\u17b6\u178f\u17b7",
16
+ "2": "\u1785\u179a\u17b6\u1785\u179a\u178e\u17cd",
17
+ "3": "\u1787\u17d2\u179a\u17bb\u1784\u1798\u17bd\u1799\u1793\u17c3\u179f\u17b6\u179f\u1793\u17b6",
18
+ "4": "\u1793\u1799\u17c4\u1794\u17b6\u1799",
19
+ "5": "\u1794\u17d2\u179b\u17c2\u1780\u17d7 \u1796\u17b8\u1793\u17c1\u17c7\u1796\u17b8\u1793\u17c4\u17c7",
20
+ "6": "\u1796\u17b6\u178e\u17b7\u1787\u17d2\u1787\u1780\u1798\u17d2\u1798",
21
+ "7": "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u1780\u17b8\u17a1\u17b6",
22
+ "8": "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u1787\u17b6\u178f\u17b7",
23
+ "9": "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u179f\u17c1\u178a\u17d2\u178b\u1780\u17b7\u1785\u17d2\u1785",
24
+ "10": "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u17a2\u1793\u17d2\u178f\u179a\u1787\u17b6\u178f\u17b7",
25
+ "11": "\u1796\u17d2\u179a\u17b9\u178f\u17d2\u178f\u17b7\u1780\u17b6\u179a\u178e\u17cd\u179f\u1784\u17d2\u1782\u1798",
26
+ "12": "\u1796\u17d2\u179a\u17b9\u178f\u17d2\u178f\u17b7\u1780\u17b6\u179a\u178e\u17cd\u17a2\u1793\u17d2\u178f\u179a\u1787\u17b6\u178f\u17b7",
27
+ "13": "\u179f\u1793\u17d2\u178a\u17b7\u179f\u17bb\u1781\u179f\u1784\u17d2\u1782\u1798",
28
+ "14": "\u179f\u17b7\u179b\u17d2\u1794\u17c8\u1793\u17b7\u1784\u178f\u17b6\u179a\u17b6",
29
+ "15": "\u179f\u17b7\u179b\u17d2\u1794\u17c8\u1793\u17b7\u1784\u179c\u1794\u17d2\u1794\u1792\u1798\u17cc",
30
+ "16": "\u179f\u17bb\u1781\u1797\u17b6\u1796",
31
+ "17": "\u179f\u17c1\u178a\u17d2\u178b\u1780\u17b7\u1785\u17d2\u1785\u179f\u17b6\u1780\u179b",
32
+ "18": "\u179f\u17c1\u179c\u17b6\u1780\u1798\u17d2\u1798",
33
+ "19": "\u179f\u17d2\u179a\u17b6\u179c\u1787\u17d2\u179a\u17b6\u179c"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "\u1780\u17b8\u17a1\u17b6\u1787\u17b6\u178f\u17b7": 0,
39
+ "\u1780\u17b8\u17a1\u17b6\u17a2\u1793\u17d2\u178f\u179a\u1787\u17b6\u178f\u17b7": 1,
40
+ "\u1785\u179a\u17b6\u1785\u179a\u178e\u17cd": 2,
41
+ "\u1787\u17d2\u179a\u17bb\u1784\u1798\u17bd\u1799\u1793\u17c3\u179f\u17b6\u179f\u1793\u17b6": 3,
42
+ "\u1793\u1799\u17c4\u1794\u17b6\u1799": 4,
43
+ "\u1794\u17d2\u179b\u17c2\u1780\u17d7 \u1796\u17b8\u1793\u17c1\u17c7\u1796\u17b8\u1793\u17c4\u17c7": 5,
44
+ "\u1796\u17b6\u178e\u17b7\u1787\u17d2\u1787\u1780\u1798\u17d2\u1798": 6,
45
+ "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u1780\u17b8\u17a1\u17b6": 7,
46
+ "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u1787\u17b6\u178f\u17b7": 8,
47
+ "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u179f\u17c1\u178a\u17d2\u178b\u1780\u17b7\u1785\u17d2\u1785": 9,
48
+ "\u1796\u17d0\u178f\u17cc\u1798\u17b6\u1793\u17a2\u1793\u17d2\u178f\u179a\u1787\u17b6\u178f\u17b7": 10,
49
+ "\u1796\u17d2\u179a\u17b9\u178f\u17d2\u178f\u17b7\u1780\u17b6\u179a\u178e\u17cd\u179f\u1784\u17d2\u1782\u1798": 11,
50
+ "\u1796\u17d2\u179a\u17b9\u178f\u17d2\u178f\u17b7\u1780\u17b6\u179a\u178e\u17cd\u17a2\u1793\u17d2\u178f\u179a\u1787\u17b6\u178f\u17b7": 12,
51
+ "\u179f\u1793\u17d2\u178a\u17b7\u179f\u17bb\u1781\u179f\u1784\u17d2\u1782\u1798": 13,
52
+ "\u179f\u17b7\u179b\u17d2\u1794\u17c8\u1793\u17b7\u1784\u178f\u17b6\u179a\u17b6": 14,
53
+ "\u179f\u17b7\u179b\u17d2\u1794\u17c8\u1793\u17b7\u1784\u179c\u1794\u17d2\u1794\u1792\u1798\u17cc": 15,
54
+ "\u179f\u17bb\u1781\u1797\u17b6\u1796": 16,
55
+ "\u179f\u17c1\u178a\u17d2\u178b\u1780\u17b7\u1785\u17d2\u1785\u179f\u17b6\u1780\u179b": 17,
56
+ "\u179f\u17c1\u179c\u17b6\u1780\u1798\u17d2\u1798": 18,
57
+ "\u179f\u17d2\u179a\u17b6\u179c\u1787\u17d2\u179a\u17b6\u179c": 19
58
+ },
59
+ "layer_norm_eps": 1e-05,
60
+ "max_position_embeddings": 514,
61
+ "model_type": "xlm-roberta",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "output_past": true,
65
+ "pad_token_id": 1,
66
+ "position_embedding_type": "absolute",
67
+ "problem_type": "single_label_classification",
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.29.1",
70
+ "type_vocab_size": 1,
71
+ "use_cache": true,
72
+ "vocab_size": 250002
73
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472917f0cbe9f5b92757b2261c61ba002416b2c3f8cd4095d9f8ba65477a2b4c
3
+ size 1112309493
runs/May13_07-43-42_152-67-0-179/1683963844.1720548/events.out.tfevents.1683963844.152-67-0-179.72779.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b373e3025e35728b2da828c400b7335a8fc4d88e139a8cab9948549366a372a1
3
+ size 5943
runs/May13_07-43-42_152-67-0-179/events.out.tfevents.1683963844.152-67-0-179.72779.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31d92e9e0cfdc7f4eb4e65ebb5bb127ea9dcd91e28046963239da08135335ca
3
+ size 8274
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14535f31bc77f152617c17b91226b17b1f75e538e6fe0084eb469699ba93b7d3
3
+ size 3963