nan-dre commited on
Commit
ea47724
1 Parent(s): 2b721ea

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "racai/distilbert-base-romanian-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "direct",
13
+ "1": "descriptive",
14
+ "2": "reporting",
15
+ "3": "offensive",
16
+ "4": "non-offensive"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "descriptive": 1,
21
+ "direct": 0,
22
+ "non-offensive": 4,
23
+ "offensive": 3,
24
+ "reporting": 2
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "output_hidden_states": true,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": true,
36
+ "tie_weights_": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.26.1",
39
+ "vocab_size": 50000
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf2f357884b3e95415a74f834eebff951c9247e51cc860d4d995a817e5d7a32
3
+ size 327701165
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "racai/distilbert-base-romanian-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "DistilBertTokenizer",
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:b2f6b1a7b0ebb480cb1e3634896c7b4e1ce7403430e5feaf1a363db54607fadd
3
+ size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff