baileyk commited on
Commit
d638aad
1 Parent(s): c6fd5c3

Training in progress, step 560

Browse files
.DS_Store ADDED
Binary file (10.2 kB). View file
 
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|BREAK|>": 50265
3
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large",
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": 384,
13
+ "id2label": {
14
+ "0": "I-SENTENCE",
15
+ "1": "B-SENTENCE"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 1536,
19
+ "label2id": {
20
+ "B-SENTENCE'": 1,
21
+ "I-SENTENCE'": 0
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 6,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.34.1",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
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 sha256:1330eb716286d021d5e985c81f800b7acd9fc70889f3a94e7060aaafb43891f8
3
+ size 120625446
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<|BREAK|>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ }
52
+ },
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": true,
55
+ "cls_token": "<s>",
56
+ "eos_token": "</s>",
57
+ "errors": "replace",
58
+ "mask_token": "<mask>",
59
+ "model_max_length": 512,
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "tokenizer_class": "RobertaTokenizer",
63
+ "trim_offsets": true,
64
+ "unk_token": "<unk>"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f340ae97637ab703b6ff6f9327c1f4717ab8496c5543f0748925a1576e004d
3
+ size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff