Hugging Face's logo

yemen2016
/
MeMo_BERT-SA_DanskBERT

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yemen2016 commited on
Commit
6202474
•
1 Parent(s): 6aba361

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. model.safetensors +1 -1
  2. runs/Mar15_11-16-40_460c4293bb46/events.out.tfevents.1710501427.460c4293bb46.1677.4 +2 -2
  3. runs/Mar15_11-23-13_460c4293bb46/events.out.tfevents.1710501804.460c4293bb46.1677.5 +3 -0
  4. tmp-checkpoint-1060/config.json +39 -0
  5. tmp-checkpoint-1060/model.safetensors +3 -0
  6. tmp-checkpoint-1060/optimizer.pt +3 -0
  7. tmp-checkpoint-1060/sentencepiece.bpe.model +3 -0
  8. tmp-checkpoint-1060/special_tokens_map.json +51 -0
  9. tmp-checkpoint-1060/tokenizer.json +0 -0
  10. tmp-checkpoint-1060/tokenizer_config.json +55 -0
  11. tmp-checkpoint-1060/training_args.bin +3 -0
  12. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4127e0f67fd157c04c707c8975bff5447fbbeb27023a46b819067f7f311d6704
3
  size 497817180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4924e436efe6251185e0574d9b8614f24cd80cb00347426372afe2f6c36344c9
3
  size 497817180
runs/Mar15_11-16-40_460c4293bb46/events.out.tfevents.1710501427.460c4293bb46.1677.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:613424485161187cd80a95d93e54538a71dfe148fd2665a479b7d953082a1643
3
- size 6116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d617e4733913dc9a76a843c18cadf7a234aa3f8874012f682c7c5459e3e5d36a
3
+ size 6650
runs/Mar15_11-23-13_460c4293bb46/events.out.tfevents.1710501804.460c4293bb46.1677.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ebd8355ae39cab8e655dd46ec5918f904417e89f524c4ae10ba1feba034155
3
+ size 5259
tmp-checkpoint-1060/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vesteinn/DanskBERT",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.38.2",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 50005
39
+ }
tmp-checkpoint-1060/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4c8fa5c647bec1a02b5ce8d48265aa76b1d238b4c31c4329321e2700dda7b47
3
+ size 497817180
tmp-checkpoint-1060/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98875d687bcce8e90a85859d8a22dd9b6dd665da4ad665cb4e50bcc3c6df1008
3
+ size 165465891
tmp-checkpoint-1060/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5226668718de0dc99d8087af7d07618fb79b6edfe028ad89c7a32576178006b6
3
+ size 1090291
tmp-checkpoint-1060/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tmp-checkpoint-1060/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tmp-checkpoint-1060/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "50004": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
tmp-checkpoint-1060/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a238799af7312f2b2fff7cfc41070af3c4310513a94ee205a976fd3f5028ffb6
3
+ size 4984
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a238799af7312f2b2fff7cfc41070af3c4310513a94ee205a976fd3f5028ffb6
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a475d2b091bc57622f12b6b52bf7cd815f0492d9515859fd8fa7dd78c07c72
3
  size 4984