dmargutierrez commited on
Commit
72de77c
1 Parent(s): ebd7c2b

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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-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": "O",
15
+ "1": "B-corporation",
16
+ "2": "I-corporation",
17
+ "3": "B-creative-work",
18
+ "4": "I-creative-work",
19
+ "5": "B-group",
20
+ "6": "I-group",
21
+ "7": "B-location",
22
+ "8": "I-location",
23
+ "9": "B-person",
24
+ "10": "I-person",
25
+ "11": "B-product",
26
+ "12": "I-product"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "B-corporation": 1,
32
+ "B-creative-work": 3,
33
+ "B-group": 5,
34
+ "B-location": 7,
35
+ "B-person": 9,
36
+ "B-product": 11,
37
+ "I-corporation": 2,
38
+ "I-creative-work": 4,
39
+ "I-group": 6,
40
+ "I-location": 8,
41
+ "I-person": 10,
42
+ "I-product": 12,
43
+ "O": 0
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "max_position_embeddings": 514,
47
+ "model_type": "xlm-roberta",
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "position_embedding_type": "absolute",
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.26.0",
55
+ "type_vocab_size": 1,
56
+ "use_cache": true,
57
+ "vocab_size": 250002
58
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5838494f02dcdb4a0e32cf3f81f5445697c5bad2877c59a79ef6eebddc328a
3
+ size 1109924909
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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94bad1e18fc10f6e584e3d666e323b232e1e3db0f3e4b24f6e513ac37e54ffb4
3
+ size 3515