Upload folder using huggingface_hub

1_Pooling/config.json

@@ -3,7 +3,5 @@
   "pooling_mode_cls_token": true,
   "pooling_mode_mean_tokens": false,
   "pooling_mode_max_tokens": false,
-  "pooling_mode_mean_sqrt_len_tokens": false,
-  "pooling_mode_weightedmean_tokens": false,
-  "pooling_mode_lasttoken": false
+  "pooling_mode_mean_sqrt_len_tokens": false
 }

README.md

@@ -9,7 +9,7 @@ datasets:
 - shunk031/jsnli
 ---
 
-# cl-nagoya/sup-simcse-ja-base
+# {MODEL_NAME}
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
@@ -29,7 +29,7 @@ Then you can use the model like this:
 from sentence_transformers import SentenceTransformer
 sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('cl-nagoya/sup-simcse-ja-base')
+model = SentenceTransformer('{MODEL_NAME}')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -52,8 +52,8 @@ def cls_pooling(model_output, attention_mask):
 sentences = ['This is an example sentence', 'Each sentence is converted']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('cl-nagoya/sup-simcse-ja-base')
-model = AutoModel.from_pretrained('cl-nagoya/sup-simcse-ja-base')
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -75,7 +75,7 @@ print(sentence_embeddings)
 
 <!--- Describe how your model was evaluated -->
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=cl-nagoya/sup-simcse-ja-base)
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
 
 
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./outputs/sup-simcse/jsnli/cl-tohoku__bert-base-japanese-v3/2023-10-02/16-22-36/",
+  "_name_or_path": "cl-tohoku/bert-base-japanese-v3",
   "architectures": [
     "BertModel"
   ],

dev-metrics.json

@@ -0,0 +1,5 @@
+{
+  "best-epoch": 0,
+  "best-step": 128,
+  "best-dev": 83.61539847191834
+}

log.csv

@@ -0,0 +1,66 @@
+epoch,step,loss,sts-dev
+0,0,inf,51.375121585435735
+0,32,5.8056640625,78.35678255256113
+0,64,3.11572265625,82.6244856578063
+0,96,2.42578125,83.35358238047021
+0,128,2.176513671875,83.61539847191834
+0,160,2.0302734375,81.87700855632563
+0,192,1.875732421875,79.53856626810594
+0,224,1.843994140625,77.77162870199022
+0,256,1.773193359375,76.12193564966829
+1,288,1.690185546875,75.82749644399787
+1,320,1.600341796875,77.40347138209835
+1,352,1.56298828125,74.4370737294954
+1,384,1.570556640625,76.08974073722088
+1,416,1.534912109375,73.89938923579099
+1,448,1.55078125,70.69398516957513
+1,480,1.509521484375,73.33702686894722
+1,512,1.545654296875,75.2034184712643
+1,544,1.52001953125,73.9900785391876
+2,576,1.463134765625,72.0822596167315
+2,608,1.376220703125,72.30434210546885
+2,640,1.373046875,75.35516784317878
+2,672,1.37646484375,75.00048637711306
+2,704,1.370849609375,71.54454915080103
+2,736,1.35595703125,72.10342263835692
+2,768,1.351318359375,73.61822488939758
+2,800,1.341552734375,73.69283818050053
+2,832,1.350341796875,73.35254646396575
+3,864,1.292724609375,71.73891113636543
+3,896,1.231201171875,72.50612877979137
+3,928,1.249267578125,71.73997216828496
+3,960,1.23486328125,72.24572646319987
+3,992,1.2470703125,72.21874965045426
+3,1024,1.260498046875,71.01279770471795
+3,1056,1.262451171875,71.28239282311822
+3,1088,1.24609375,72.01843871324893
+3,1120,1.25048828125,71.49440820181441
+4,1152,1.151611328125,69.90122275478602
+4,1184,1.157958984375,71.99470697954118
+4,1216,1.179931640625,69.07210383354008
+4,1248,1.173828125,67.60162600897702
+4,1280,1.152587890625,68.50119537305783
+4,1312,1.176513671875,69.20852332481955
+4,1344,1.166015625,69.92232791766861
+4,1376,1.1796875,71.00892896894848
+5,1408,1.16357421875,72.45555003088666
+5,1440,1.0804443359375,69.45015860800906
+5,1472,1.0814208984375,71.00156597627819
+5,1504,1.1224365234375,70.58322578457057
+5,1536,1.097412109375,69.09835049406871
+5,1568,1.097412109375,70.2241604764949
+5,1600,1.1026611328125,71.35726715857705
+5,1632,1.1053466796875,69.87296046317874
+5,1664,1.11376953125,70.50921749290218
+6,1696,1.092529296875,70.10898081907449
+6,1728,1.0654296875,70.09196262215698
+6,1760,1.068603515625,69.50168151188232
+6,1792,1.0595703125,68.94335544010495
+6,1824,1.048583984375,68.59140278421327
+6,1856,1.0460205078125,69.62795505629208
+6,1888,1.0633544921875,69.44217502657546
+6,1920,1.0531005859375,69.53616592289175
+6,1952,1.0594482421875,69.40128536108074
+7,1984,1.044189453125,69.35274684809701
+7,2016,1.013427734375,69.4939563818511
+7,2048,1.0462646484375,69.50480224133872

sts-metrics.json

@@ -0,0 +1,6 @@
+{
+  "jsick": 82.7495424766893,
+  "jsts-val": 80.8645208379796,
+  "jsts-train": 77.85762915212484,
+  "avg": 80.49056415559791
+}