lucafrost commited on
Commit
3578a36
1 Parent(s): 682b954

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "None",
13
+ "1": "Quote-SpeakerRight",
14
+ "2": "Speaker",
15
+ "3": "Quote-SpeakerLeft",
16
+ "4": "Quote-Unknown"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "None": 0,
21
+ "Quote-SpeakerLeft": 3,
22
+ "Quote-SpeakerRight": 1,
23
+ "Quote-Unknown": 4,
24
+ "Speaker": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "qa_dropout": 0.1,
33
+ "seq_classif_dropout": 0.2,
34
+ "sinusoidal_pos_embds": false,
35
+ "tie_weights_": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.26.0",
38
+ "vocab_size": 28996
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c01c54491656f62d6719ef649749f9d4098ce01fa338bd01e611b7ed7087e55
3
+ size 260812661
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a31500ba86591784388015ae4c05c12a396ad558f367841bebc56383d58f20
3
+ size 3503
vocab.txt ADDED
The diff for this file is too large to render. See raw diff