Upload folder using huggingface_hub

1_Pooling/config.json

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

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: sentence-transformers
 pipeline_tag: sentence-similarity
 tags:
 - sentence-transformers
@@ -85,7 +86,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 414 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 7981 with parameters:
 ```
 {'batch_size': 1, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -97,8 +98,8 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 2,
-    "evaluation_steps": 500,
+    "epochs": 1,
+    "evaluation_steps": 1000,
     "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
@@ -117,7 +118,7 @@ Parameters of the fit()-Method:
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
-  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
 )
 ```
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/symanto_sn-xlm-roberta-base-snli-mnli-anli-xnli/",
+  "_name_or_path": "dadashzadeh/xlm-roberta-base-test",
   "architectures": [
     "XLMRobertaModel"
   ],

eval/similarity_evaluation_results.csv

@@ -1,3 +1,13 @@
 epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
-0,-1,0.8355244163453055,0.6282459709409298,0.8339586108310645,0.6216201305288228,0.8316541367052884,0.6224529587431137,0.7847741806720513,0.6230549552739728
-1,-1,0.8476684996903473,0.6438837617957465,0.8459151905293754,0.6273070485318208,0.8443433034653669,0.6272330293261338,0.8179680560698438,0.6457642709192574
+0,500,0.8210297800992388,0.735131359757495,0.8209519766004953,0.7323958693465276,0.8183538605809872,0.7260243086929091,0.8051560263954539,0.7267218055876611
+0,1000,0.8350159680996591,0.7538546912188798,0.8293936614660378,0.7495487547039875,0.8280018003553223,0.744381363469144,0.822020364016452,0.7467479805638917
+0,1500,0.8363667072274277,0.7467786036077396,0.8256833488492993,0.7382411548196435,0.8235512176819711,0.7332058424845307,0.8178339719671923,0.7385189551917144
+0,2000,0.8326432499013147,0.7397769449308852,0.8285183555073171,0.7407764066439287,0.8264556147484639,0.7352502502548202,0.8117228058006722,0.7286051745787337
+0,1000,0.8618216184494492,0.7647567323709974,0.855939198227748,0.7625484769703583,0.8544927001830012,0.755953559054206,0.8473217377731791,0.7555450098752372
+0,2000,0.8619012315650276,0.7626736145017022,0.8584390647803921,0.7576231716454502,0.8562511281937888,0.7524290394206343,0.8357092296164098,0.7471687157833198
+0,3000,0.8771815791514924,0.7767261807732394,0.8698010555140848,0.7679121918271429,0.8682319970663711,0.76241327648906,0.8541910011888496,0.7624107578299769
+0,4000,0.896627514227454,0.7887439322113436,0.8870658838133475,0.7845757396184716,0.8864605814650639,0.780604491503738,0.8838423219759,0.7799116750119877
+0,5000,0.9015582756466218,0.7903064536132656,0.8924817485608807,0.7843869889575948,0.8916062549773747,0.7802168956877107,0.8834128568839786,0.7808502229699049
+0,6000,0.8956473387051668,0.7898903621911975,0.8860461939398799,0.7816313891564726,0.8853431911714782,0.7780054790758091,0.8772639027893181,0.7799160402140173
+0,7000,0.9101511572910473,0.8000948362011497,0.8967603706182512,0.7857255532514853,0.8963164678414524,0.7824885988037533,0.8876645729694481,0.7910586689718305
+0,-1,0.9151936179146087,0.8014666305260926,0.9017840881954231,0.7906026505738841,0.9013502149310223,0.787623428272791,0.8951089984942956,0.793243876995732

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84b30876608eca9006e984bb98efddb0c20936be5a0a490fa189d2efead2c41d
+oid sha256:17353fc86fcd0974ab3450172d4071dae1a775c5e985b0f48343760948d01157
 size 1112197096

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }