Hugging Face's logo

pgajo
/
mbert-xlwa-en-it_EW-TT-PE_U0_S1_Tingredient_P0.75_DROP1_mbert_E7_DEV92.0

Question Answering
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
pgajo commited on
Commit
996f0f9
•
1 Parent(s): 9f099fa

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +31 -0
  2. metrics.tsv +11 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +55 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pgajo/mbert-xlwa-en-it",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.37.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
metrics.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch train_loss train_f1 train_exact dev_loss dev_f1 dev_exact test_loss test_f1 test_exact
2
+ 1 0.7719278225432271 79.52947448859554 64.94490358126721 0.37337882444262505 91.59556560655463 84.61538461538461 0 0 0
3
+ 2 0.20413360582745593 94.44341525725213 89.60055096418733 0.33021537711222965 94.43942809327424 90.10989010989012 0 0 0
4
+ 3 0.0944768785316821 97.6436161742433 95.59228650137742 0.4031308473398288 92.82780711352142 89.01098901098901 0 0 0
5
+ 4 0.05001066402410683 98.68079576811634 97.38292011019284 0.36196490765238803 94.18621294671715 90.10989010989012 0 0 0
6
+ 5 0.030056177744763376 99.31963436642582 98.4159779614325 0.3473975524927179 94.3366157651872 90.38461538461539 0 0 0
7
+ 6 0.036456696730253854 98.9240347194893 98.14049586776859 0.4160988898947835 94.99857285571572 90.38461538461539 0 0 0
8
+ 7 0.020396103414342455 99.37515844753989 98.89807162534436 0.4281040045122306 94.67937816152103 92.03296703296704 0 0 0
9
+ 8 0.013906667820739804 99.59074213206443 99.31129476584022 0.3941942236075799 94.8467626695649 90.93406593406593 0 0 0
10
+ 9 0.01627988931242093 99.77043158861342 99.72451790633609 0.41736091890682775 94.61145996860283 91.20879120879121 0 0 0
11
+ 10 0.022256465652785468 99.17724536893198 98.55371900826447 0.4191143736243248 95.14768378213759 91.75824175824175 0 0 0
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09e1c5e3a5af666d5e0c7e7d86c6ff167f05e6a70d719b74382a9f85695a559
3
+ size 709080904
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff