noah-go commited on
Commit
fb42a6c
1 Parent(s): 7bf241f

initial commit

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md ADDED
File without changes
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-base",
3
+ "architectures": [
4
+ "RobertaModel"
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
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizer",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.13.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.1.0",
4
+ "transformers": "4.13.0",
5
+ "pytorch": "1.7.0+cu110"
6
+ }
7
+ }
eval/similarity_evaluation_sts-dev_results.csv ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,-1,0.8603829184143664,0.8634439808588751,0.8520373126043029,0.8582637518032019,0.8519665769908871,0.8582077748963437,0.8305067668652699,0.8297689706234703
3
+ 1,-1,0.8738941526987756,0.8732814736395488,0.8572646949316028,0.8637278623258947,0.8572464105288398,0.863677852383028,0.8453502241053964,0.8435598021802103
4
+ 2,-1,0.8696573041220188,0.8715316450173949,0.8582154646347402,0.8656908761326176,0.8576657264057793,0.8649860002025886,0.8390346407149374,0.8374201573846959
5
+ 3,-1,0.8750163944562664,0.8760740592164935,0.8614311434759245,0.8692434586491514,0.8606418133936148,0.8685416716892201,0.8461674597377774,0.8451364687459089
6
+ 4,-1,0.8751659863714976,0.8759995162362965,0.8613002432395667,0.8694394249762125,0.860629998153408,0.8687313337414789,0.8472061320718693,0.8454604049119452
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0143341f5e4653b7ece14cf0685f5fbf5b68a3926beed43754a498947c3bd77
3
+ size 442558967
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
similarity_evaluation_sts-test_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ -1,-1,0.8477045280392909,0.8559956140722809,0.8370636752767797,0.8440079435411166,0.8370234533153658,0.8438439443425015,0.8241822253054464,0.8233260855548581
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5b1f4865d09eaa42f5c27660916c3c9e9fc2126ea562c99da0f9834db70602
3
+ size 442739392
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "bos_token": "[CLS]", "eos_token": "[SEP]", "model_max_length": 512, "special_tokens_map_file": "/home/jhgan/.cache/huggingface/transformers/9d0c87e44b00acfbfbae931b2e4068eb6311a0c3e71e23e5400bdf57cab4bfbf.70c17d6e4d492c8f24f5bb97ab56c7f272e947112c6faf9dd846da42ba13eb23", "name_or_path": "klue/roberta-base", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff