Hugging Face's logo

btamm12
/
robbert-2023-dutch-large-nelf

Fill-Mask
Transformers
PyTorch
TensorBoard
roberta
Inference Endpoints
Model card Files Metrics Community
btamm12 commited on
Commit
de770fe
•
1 Parent(s): 72b7b0d

Training in progress, step 200

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +33 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. runs/Apr15_16-26-25_aristoteles.esat.kuleuven.be/1713191279.5286767/events.out.tfevents.1713191279.aristoteles.esat.kuleuven.be.3335488.1 +3 -0
  6. runs/Apr15_16-26-25_aristoteles.esat.kuleuven.be/events.out.tfevents.1713191279.aristoteles.esat.kuleuven.be.3335488.0 +3 -0
  7. runs/Apr15_16-29-46_aristoteles.esat.kuleuven.be/1713191458.2738898/events.out.tfevents.1713191458.aristoteles.esat.kuleuven.be.3336762.1 +3 -0
  8. runs/Apr15_16-29-46_aristoteles.esat.kuleuven.be/events.out.tfevents.1713191458.aristoteles.esat.kuleuven.be.3336762.0 +3 -0
  9. runs/Apr15_16-33-23_aristoteles.esat.kuleuven.be/1713191671.9959233/events.out.tfevents.1713191671.aristoteles.esat.kuleuven.be.3338105.1 +3 -0
  10. runs/Apr15_16-33-23_aristoteles.esat.kuleuven.be/events.out.tfevents.1713191671.aristoteles.esat.kuleuven.be.3338105.0 +3 -0
  11. runs/Apr15_16-42-47_aristoteles.esat.kuleuven.be/1713192232.6492043/events.out.tfevents.1713192232.aristoteles.esat.kuleuven.be.3341282.1 +3 -0
  12. runs/Apr15_16-42-47_aristoteles.esat.kuleuven.be/events.out.tfevents.1713192232.aristoteles.esat.kuleuven.be.3341282.0 +3 -0
  13. runs/Apr15_16-47-11_aristoteles.esat.kuleuven.be/1713192535.7034795/events.out.tfevents.1713192535.aristoteles.esat.kuleuven.be.3343187.1 +3 -0
  14. runs/Apr15_16-47-11_aristoteles.esat.kuleuven.be/events.out.tfevents.1713192535.aristoteles.esat.kuleuven.be.3343187.0 +3 -0
  15. runs/Apr15_16-51-13_aristoteles.esat.kuleuven.be/1713192816.1896539/events.out.tfevents.1713192816.aristoteles.esat.kuleuven.be.3344947.1 +3 -0
  16. runs/Apr15_16-51-13_aristoteles.esat.kuleuven.be/events.out.tfevents.1713192816.aristoteles.esat.kuleuven.be.3344947.0 +3 -0
  17. special_tokens_map.json +51 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +65 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DTAI-KULeuven/robbert-2023-dutch-large",
3
+ "additional_special_tokens_ids": [],
4
+ "architectures": [
5
+ "RobertaForMaskedLM"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "cls_token_id": 0,
11
+ "eos_token_id": 1,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "layer_norm_eps": 1e-05,
18
+ "mask_token_id": 4,
19
+ "max_position_embeddings": 514,
20
+ "model_type": "roberta",
21
+ "num_attention_heads": 16,
22
+ "num_hidden_layers": 24,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "sep_token_id": 3,
26
+ "tokenizer_class": "RobertaTokenizerFast",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.27.4",
29
+ "type_vocab_size": 1,
30
+ "unk_token_id": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 50000
33
+ }
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:a5ab677430ec4bb476e686618acf09a44e9c93e46f017fe4818ac5954d049ab4
3
+ size 1420699179
runs/Apr15_16-26-25_aristoteles.esat.kuleuven.be/1713191279.5286767/events.out.tfevents.1713191279.aristoteles.esat.kuleuven.be.3335488.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adac0fb9522eeff636a90a4ddb4fbdc26303e788ea5a66a6ec73cdc7974b7366
3
+ size 5887
runs/Apr15_16-26-25_aristoteles.esat.kuleuven.be/events.out.tfevents.1713191279.aristoteles.esat.kuleuven.be.3335488.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d62d6f25aef8460e3231c7f782cd40011778ce6ef820ac349f837dc5be4a4ec
3
+ size 4455
runs/Apr15_16-29-46_aristoteles.esat.kuleuven.be/1713191458.2738898/events.out.tfevents.1713191458.aristoteles.esat.kuleuven.be.3336762.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4760532fa42881ba1e65b0e911dcc6f876519709fbf5fbde36817a974ee5cd59
3
+ size 5887
runs/Apr15_16-29-46_aristoteles.esat.kuleuven.be/events.out.tfevents.1713191458.aristoteles.esat.kuleuven.be.3336762.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e898226f5a8424f83f45d2aa347faa594110f6cc3d4a2d217bd3e633130d2cf2
3
+ size 4454
runs/Apr15_16-33-23_aristoteles.esat.kuleuven.be/1713191671.9959233/events.out.tfevents.1713191671.aristoteles.esat.kuleuven.be.3338105.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3931ba5aef5a0edd1c336c4d69d72a4456b700614d3d3aea0aefff5636246840
3
+ size 5887
runs/Apr15_16-33-23_aristoteles.esat.kuleuven.be/events.out.tfevents.1713191671.aristoteles.esat.kuleuven.be.3338105.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2075aa39a56c14b2f5033d570731ea012dbd85de2254819493a97079f14375ea
3
+ size 4456
runs/Apr15_16-42-47_aristoteles.esat.kuleuven.be/1713192232.6492043/events.out.tfevents.1713192232.aristoteles.esat.kuleuven.be.3341282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5497af2019d4658eac63937417a31741080fa61df8f6c0c6d19bc8b34038b1e
3
+ size 5887
runs/Apr15_16-42-47_aristoteles.esat.kuleuven.be/events.out.tfevents.1713192232.aristoteles.esat.kuleuven.be.3341282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c922255d5914516fe852768f609a713560610c120fb38499c286aef573d8d0
3
+ size 4456
runs/Apr15_16-47-11_aristoteles.esat.kuleuven.be/1713192535.7034795/events.out.tfevents.1713192535.aristoteles.esat.kuleuven.be.3343187.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978ec3dd841d5ecc1de6cdb7e8f23dbfb6986699b8c690f126c62d912f3adfc1
3
+ size 5887
runs/Apr15_16-47-11_aristoteles.esat.kuleuven.be/events.out.tfevents.1713192535.aristoteles.esat.kuleuven.be.3343187.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0167702693cc3b9f2556e0a8b1a789803cb6fb53a98d5e5b3dc0edb178b2ebfc
3
+ size 4456
runs/Apr15_16-51-13_aristoteles.esat.kuleuven.be/1713192816.1896539/events.out.tfevents.1713192816.aristoteles.esat.kuleuven.be.3344947.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b6253ad1896bc216be9cfdf3815c07d4328636b505a0b0d0982087c479f974
3
+ size 5887
runs/Apr15_16-51-13_aristoteles.esat.kuleuven.be/events.out.tfevents.1713192816.aristoteles.esat.kuleuven.be.3344947.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b51a9406e8a78dd4ae13dcc255ee6a7af79cfc9f2639b4f9ad530e0e93215ad
3
+ size 5305
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
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": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 512,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/users/psi/btamm/.cache/huggingface/hub/models--DTAI-KULeuven--robbert-2023-dutch-large/snapshots/e6de573eb5e0d125588808ad18699ad0a86ff963/special_tokens_map.json",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7faa6905b70b508bb8728c214071d7c9fab10e7221a946b3cc773297809d01
3
+ size 3567
vocab.json ADDED
The diff for this file is too large to render. See raw diff