emilys commited on
Commit
d1490e5
1 Parent(s): 2577bdf

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-roberta-base-dec2021",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "ner",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 3,
20
+ "4": 4,
21
+ "5": 5,
22
+ "6": 6,
23
+ "7": 7,
24
+ "8": 8,
25
+ "9": 9,
26
+ "10": 10,
27
+ "11": 11,
28
+ "12": 12
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "0": 0,
34
+ "1": 1,
35
+ "2": 2,
36
+ "3": 3,
37
+ "4": 4,
38
+ "5": 5,
39
+ "6": 6,
40
+ "7": 7,
41
+ "8": 8,
42
+ "9": 9,
43
+ "10": 10,
44
+ "11": 11,
45
+ "12": 12
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "max_position_embeddings": 514,
49
+ "model_type": "roberta",
50
+ "num_attention_heads": 12,
51
+ "num_hidden_layers": 12,
52
+ "pad_token_id": 1,
53
+ "position_embedding_type": "absolute",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.20.1",
56
+ "type_vocab_size": 1,
57
+ "use_cache": true,
58
+ "vocab_size": 50265
59
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b234148bff32703b0cea78d66e0d305f58aade832e2a0596e01040ac9cabec
3
+ size 496331185
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "cardiffnlp/twitter-roberta-base-dec2021",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f6d1570daf3689508dd519f100decb7441960647870dfb3a2168e6eca6bd9e
3
+ size 3311
vocab.json ADDED
The diff for this file is too large to render. See raw diff