Ubuntu
commited on
Commit
•
6201b5e
1
Parent(s):
8d527b5
added model
Browse files- 0_Transformer/added_tokens.json +1 -0
- 0_Transformer/config.json +27 -0
- 0_Transformer/pytorch_model.bin +3 -0
- 0_Transformer/sentence_bert_config.json +4 -0
- 0_Transformer/sentencepiece.bpe.model +3 -0
- 0_Transformer/special_tokens_map.json +1 -0
- 0_Transformer/tokenizer_config.json +1 -0
- 1_Pooling/config.json +7 -0
- config.json +3 -0
- modules.json +14 -0
- similarity_evaluation_sts-dev_results.csv +5 -0
- similarity_evaluation_sts-test_results.csv +2 -0
0_Transformer/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"IDeagerbeaverID": 250023, "IDcottoncandyID": 250017, "IDconartistID": 250015, "IDprivateeyeID": 250047, "IDcellularphoneID": 250011, "IDnarrowescapeID": 250042, "IDbusybeeID": 250009, "IDbananarepublicID": 250005, "IDcomputerprogramID": 250014, "IDhomerunID": 250033, "IDhighlifeID": 250032, "IDswansongID": 250056, "IDelbowroomID": 250025, "IDmentaldisorderID": 250040, "IDpillowslipID": 250046, "IDdreamticketID": 250020, "IDflowerchildID": 250028, "IDbadappleID": 250003, "IDinsurancecompanyID": 250034, "IDpeaceconferenceID": 250044, "IDgooseeggID": 250030, "IDsacredcowID": 250050, "IDloansharkID": 250037, "IDbirthrateID": 250007, "IDtravelguideID": 250059, "IDentrancehallID": 250026, "IDcriticalreviewID": 250018, "IDmailinglistID": 250038, "IDpublicserviceID": 250048, "IDsittingduckID": 250053, "IDphonebookID": 250045, "IDmailserviceID": 250039, "IDfoodmarketID": 250029, "IDcookingstoveID": 250016, "IDthinktankID": 250057, "IDmiddleschoolID": 250041, "IDsugardaddyID": 250055, "IDtopdogID": 250058, "IDlifevestID": 250036, "IDskintoneID": 250054, "IDbigfishID": 250006, "IDsexbombID": 250051, "IDricepaperID": 250049, "IDdrylandID": 250021, "IDfishstoryID": 250027, "IDpandacarID": 250043, "IDancienthistoryID": 250002, "IDsilverliningID": 250052, "IDeconomicaidID": 250024, "IDdisabilityinsuranceID": 250019, "IDchainreactionID": 250012, "IDweddinganniversaryID": 250060, "IDclosedbookID": 250013, "IDcallcentreID": 250010, "IDduststormID": 250022, "IDbadhatID": 250004, "IDbowtieID": 250008, "IDweddingdayID": 250061, "IDlabourunionID": 250035, "IDhealthcheckID": 250031}
|
0_Transformer/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/tmp/",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"transformers_version": "4.5.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 250062
|
27 |
+
}
|
0_Transformer/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86b6b3181d693ab72b278150d05769e0f8cb291babcd611b4978edb36d1d50b0
|
3 |
+
size 1112445495
|
0_Transformer/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": null,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
0_Transformer/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
0_Transformer/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
0_Transformer/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "truncation": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/ubuntu/tmp/"}
|
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 |
+
}
|
config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": "1.1.0"
|
3 |
+
}
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "0_Transformer",
|
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 |
+
]
|
similarity_evaluation_sts-dev_results.csv
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
|
2 |
+
0,-1,0.8119324812996779,0.8116776740264294,0.8079598693254805,0.8080683903968343,0.8125507930319158,0.8125847885314423,0.7393989975377739,0.7410847658789051
|
3 |
+
1,-1,0.8340640164275451,0.8327758060241979,0.8178253816378657,0.8199581530504849,0.8251972799035385,0.827333489101137,0.7835310860593381,0.782743963667508
|
4 |
+
2,-1,0.8470769619381483,0.8470494571969245,0.824696948218016,0.8281107601001736,0.8305400946437699,0.8336738305166499,0.801844338548842,0.8029884384925288
|
5 |
+
3,-1,0.8481279257284737,0.848937057390773,0.8281351341046772,0.8319336346245011,0.832825318363582,0.8362215521743861,0.8033388808039743,0.8053677942270742
|
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,-1,0.8207584595442614,0.8167355640990784,0.8003737466777974,0.7961900411241559,0.8074380273472532,0.8019492571464516,0.7654673820185469,0.756567631993388
|