gregorgabrovsek commited on
Commit
393754a
1 Parent(s): c45bee9

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EMBEDDIA/sloberta",
3
+ "architectures": [
4
+ "CamembertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1",
17
+ "2": "2",
18
+ "3": "3",
19
+ "4": "4",
20
+ "5": "OOC"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "0": 0,
26
+ "1": 1,
27
+ "2": 2,
28
+ "3": 3,
29
+ "4": 4,
30
+ "OOC": 5
31
+ },
32
+ "layer_norm_eps": 1e-05,
33
+ "max_position_embeddings": 514,
34
+ "model_type": "camembert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.26.1",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 32005
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51fd2a4aa4f83558229b3df13ae4adccc2e0931ec8eb45295ec719004c289114
3
+ size 442581079
runs/Apr12_10-22-27_wn203.arnes.si/1681287759.2443645/events.out.tfevents.1681287759.wn203.arnes.si.1637911.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766c9d6c72abaa79c27e28dff34d5285c5540ec8edf3f4c5c79c8348bf37ab9a
3
+ size 5795
runs/Apr12_10-22-27_wn203.arnes.si/events.out.tfevents.1681287759.wn203.arnes.si.1637911.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa32c768c321935ab5a0c743ebb6430c336c0a97d8faedd5e816d818903f1d5
3
+ size 7807
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "do_lower_case": false,
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<mask>",
13
+ "lstrip": true,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "model_max_length": 512,
19
+ "name_or_path": "EMBEDDIA/sloberta",
20
+ "pad_token": "<pad>",
21
+ "sep_token": "</s>",
22
+ "sp_model_kwargs": {},
23
+ "special_tokens_map_file": null,
24
+ "tokenizer_class": "CamembertTokenizer",
25
+ "unk_token": "<unk>"
26
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62693e5fe455c57ff15a603116bcb2a5013d3a98e1341dc5965b389de8b6648
3
+ size 3503