themohal commited on
Commit
9bf6786
1 Parent(s): 67bc52a

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "position_embedding_type": "absolute",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.30.0.dev0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
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 sha256:2daf1e22ad2627aad5df38bcd7c93d82cb563471f5f3c5fa299f115db7c2931a
3
+ size 496314413
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc91da2ebc198c9572aac787bf00b760697da621548dc8b04cc857b19200239
3
+ size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff