Hugging Face's logo

yosriku
/
exp_data_scale_3files

Sentence Similarity
sentence-transformers
TensorBoard
Safetensors
albert
feature-extraction
Generated from Trainer
dataset_size:3801
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
Model card Files
xet
 Metrics Community
yosriku commited on
Commit
a2ef704
·
verified ·
1 Parent(s): ae49d8d

Training in progress, step 5

Browse files
Files changed (9) hide show
  1. config.json +48 -0
  2. eval/triplet_evaluation_retrieval-validation_results.csv +2 -0
  3. model.safetensors +3 -0
  4. runs/Nov06_23-48-56_de077089cc8e/events.out.tfevents.1762472939.de077089cc8e.37.9 +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +65 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 5,
3
+ "architectures": [
4
+ "AlbertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "LABEL_0",
18
+ "1": "LABEL_1",
19
+ "2": "LABEL_2",
20
+ "3": "LABEL_3",
21
+ "4": "LABEL_4"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "inner_group_num": 1,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "albert",
36
+ "net_structure_type": 0,
37
+ "num_attention_heads": 12,
38
+ "num_hidden_groups": 1,
39
+ "num_hidden_layers": 12,
40
+ "num_memory_blocks": 0,
41
+ "output_past": true,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.53.3",
46
+ "type_vocab_size": 2,
47
+ "vocab_size": 30000
48
+ }
eval/triplet_evaluation_retrieval-validation_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,accuracy_cosine
2
+ 0.3333333333333333,5,0.989880383014679
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65371a111d83ceb600265785f820061d2fbdbdd702891241b38b32224b083692
3
+ size 46737416
runs/Nov06_23-48-56_de077089cc8e/events.out.tfevents.1762472939.de077089cc8e.37.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce62f0b31a698714b2131a6cbef8137fc03e39e2b5ac09f56dfcb4e34081763
3
+ size 4784
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 32,
51
+ "model_max_length": 32,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45017dfb5127a23d9c1298b7a183e94d040854a293f54fdd780e0fe8fedaa727
3
+ size 5624
vocab.txt ADDED
The diff for this file is too large to render. See raw diff