Upload 12 files

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

README.md

@@ -1,3 +1,87 @@
 ---
-license: openrail
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
 ---
+
+# {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.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- 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={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 24855 with parameters:
+```
+{'batch_size': 256, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 5,
+    "evaluation_steps": 6000,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 6000,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/user/smadani/.cache/torch/sentence_transformers/sentence-transformers_all-mpnet-base-v2/",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,26 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,6000,0.7705983141674634,0.7588410765997566,0.7460866133571115,0.7588409194986603,0.7460196340124199,0.7583741883113354,0.7705983144051983,0.7588409193253192
+0,12000,0.7890708590630007,0.7717662038224076,0.7657517620833345,0.7717662033649667,0.7658501737655569,0.771530708776096,0.7890708588357381,0.7717662045016314
+0,18000,0.7989500289377678,0.7804163890975293,0.7762049247088953,0.7804163900401087,0.7764791637867681,0.7803444399334862,0.7989500281277483,0.7804166019786863
+0,24000,0.8030339818318738,0.7829832500550294,0.7809943470749454,0.7829832507202608,0.7809796874459198,0.7826594770812045,0.8030339814524897,0.7829832493277981
+0,-1,0.8009557271543037,0.7805823031759661,0.7805424806895,0.7805823023720204,0.7804498252950408,0.7802254871218193,0.800955727092346,0.7805823030442471
+1,6000,0.8073723349466574,0.7863297896519679,0.7842878819763555,0.7863297891175831,0.7842116380618542,0.7860381303428672,0.8073723338855715,0.7863297892192027
+1,12000,0.8058417139291039,0.7853900056226056,0.7864925727642911,0.7853900046522265,0.786154246362743,0.7847415501717939,0.8058417140505345,0.7853900065126332
+1,18000,0.8113867584164989,0.7894462950957082,0.7883637190471253,0.78944629444399,0.7880311867111743,0.7888685394551394,0.8113867587891529,0.7894462959064469
+1,24000,0.8136074130413401,0.7912111996064499,0.7890980356771737,0.7912111982856123,0.7886681367201622,0.7904812273361662,0.8136074133277406,0.7912111985007747
+1,-1,0.8148753484791565,0.7928271165911006,0.7910503153275671,0.7928271163478682,0.7906903528848861,0.7922664861219498,0.8148753494014288,0.7928271157518523
+2,6000,0.8154129398329505,0.793216701381966,0.7915641409348209,0.7932167012638446,0.7912033007750121,0.7926588220416374,0.8154129400583746,0.7932167014442014
+2,12000,0.8164994641188084,0.7936501776859877,0.7907609775653783,0.7936501353074314,0.7901868156457241,0.7928485584622326,0.8164994633163214,0.7936501337068416
+2,18000,0.8169088326038305,0.7940242044630016,0.7925981617252766,0.7940241616487277,0.791854228829219,0.7930770429272399,0.8169088324514927,0.794024202973127
+2,24000,0.817381603637144,0.7942456461994725,0.7938404278735067,0.794245646718646,0.7929595813863601,0.7931616299721707,0.8173816045214284,0.7942456477312998
+2,-1,0.8185604144860281,0.7951918790861693,0.7931898716757719,0.7951918790099678,0.7924681210653997,0.794236095936382,0.8185604140474608,0.79519187986927
+3,6000,0.8193032803679741,0.7961087927943666,0.7940293504687437,0.7961087930091338,0.793154788414539,0.7950743200628629,0.8193032811230874,0.7961087915192893
+3,12000,0.8197369795013651,0.7965322582782887,0.7944689704949262,0.7965322580684167,0.7935607551234761,0.7954655685014532,0.8197369794781375,0.7965324174650629
+3,18000,0.8205325959948845,0.7970379923136904,0.7950646479929744,0.7970379927359682,0.7940318074741194,0.7958553883176431,0.8205325943318713,0.7970379905522855
+3,24000,0.8210258874152909,0.7973519554230893,0.7954329061475902,0.7973519466285548,0.7944299823663004,0.7961594670666294,0.8210258882659311,0.7973519458742141
+3,-1,0.8197625832707419,0.7960490278726131,0.7952791568334892,0.7960490286070598,0.7940967097548686,0.7946291495871929,0.8197625835547221,0.7960490275050291
+4,6000,0.8206867927654762,0.7968466840352273,0.7954804387705738,0.7968466839241598,0.7943709438539766,0.7955688217063781,0.8206867923658062,0.7968468493310414
+4,12000,0.8206924782959505,0.7971168102226616,0.7958351665765877,0.7971168104374906,0.7946871011099879,0.7957988169630384,0.8206924794519317,0.7971168101394549
+4,18000,0.8218455528365036,0.7980237509205957,0.7960749680999324,0.7980235814098676,0.795001300955575,0.7967852671167873,0.8218455536561325,0.7980235868506562
+4,24000,0.8213873313501759,0.797632686420526,0.7962854364032825,0.7976326866146097,0.7951608660063313,0.7963457863302134,0.8213873318744489,0.7976326863862572
+4,-1,0.8213716630249875,0.7976205728576652,0.7962610655915265,0.797620572808963,0.7951433958969236,0.7963369599882939,0.8213716632503943,0.7976205725251677

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637968c7637e60b55f601cafd534181869808498b732c25542e7df55739f1615
+size 438014769

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "/user/smadani/.cache/torch/sentence_transformers/sentence-transformers_all-mpnet-base-v2/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}