Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "jjzha/jobbert-base-cased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

.ipynb_checkpoints/config_sentence_transformers-checkpoint.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "1.13.1"
+  }
+}

1_Pooling/.ipynb_checkpoints/config-checkpoint.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
+}

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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 384, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddedaff841cfba85d96fe8c77c9453b6b52f45eef8bdb257f2229a381f05099e
+size 1182399

README.md

@@ -0,0 +1,91 @@
+---
+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 384 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 13952 with parameters:
+```
+{'batch_size': 14, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters:
+  ```
+  {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 2000,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 10000,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (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): Dense({'in_features': 768, 'out_features': 384, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "jjzha/jobbert-base-cased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "1.13.1"
+  }
+}

eval/.ipynb_checkpoints/similarity_evaluation_results-checkpoint.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,2000,0.9620967570857263,0.8656843900989896,0.9576860826125646,0.8655457297383932,0.956790631706535,0.8655465200901662,0.9443489366012364,0.8646869422200442

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
+0,2000,0.9620967570857263,0.8656843900989896,0.9576860826125646,0.8655457297383932,0.956790631706535,0.8655465200901662,0.9443489366012364,0.8646869422200442
+0,4000,0.9757625739396699,0.8659520987313962,0.9721630045633578,0.8658829196050186,0.9718497713198054,0.8658844421951383,0.9477962904266586,0.8653547318060353
+0,6000,0.9763679739999793,0.8659845496846734,0.9771342988517222,0.8658887775087574,0.9769248345200108,0.865898796389763,0.958424355075297,0.8657110760940272
+0,8000,0.968420698159747,0.8659819694384423,0.9814136282279418,0.8659398249712291,0.9812167123117663,0.8659458455977739,0.9570578065403882,0.8656307042408063
+0,10000,0.9588003738341574,0.8658677751883797,0.9776970484979342,0.8658010019106682,0.9767258142086378,0.8657948534362276,0.9543490568677792,0.865516556445657
+0,12000,0.9736717020053842,0.8660080975507602,0.9754315366463718,0.8659926972141372,0.9757216334053973,0.8659936502867528,0.955879337650436,0.8658051047712958
+0,-1,0.9672764702295693,0.8659194619653063,0.9795469480098705,0.8658939961594514,0.9795998615935617,0.8659042358706204,0.9625427410425603,0.8656422863891527
+1,2000,0.9728529400967733,0.8659272375962298,0.9798027368504951,0.8659100124145628,0.9800596835186687,0.8659131738248675,0.9725344221339278,0.8657798716151341
+1,4000,0.964557775339131,0.8658773176121489,0.9803417136427685,0.8659184040957124,0.9802017563832188,0.8659129878587261,0.9660521200901877,0.8656914800101909
+1,6000,0.9710684204058313,0.8659298295839918,0.9827374551159173,0.8658937520763136,0.9825219290879302,0.8658880685157098,0.9675807947609758,0.8657373320656621
+1,8000,0.9719213708807937,0.8659649073114143,0.9808081920937366,0.8659060606530202,0.9812651909588999,0.8659289343795465,0.9708419695022548,0.8658963439778603
+1,10000,0.9551920879253551,0.8658861742951324,0.9825550098556257,0.865970857921808,0.9819672911005527,0.865972996521101,0.9605386895381901,0.8657300678047237
+1,12000,0.965337360816363,0.8659492165404664,0.9821582007163127,0.8659534120552745,0.982167153300361,0.8659604089984845,0.969349835794043,0.8658010716594159
+1,-1,0.9599416843632763,0.8660102595451264,0.9838700375616571,0.8660050522803713,0.9826244974705571,0.8660071095198678,0.9626400582295737,0.8658476210810014
+2,2000,0.9709350537370208,0.8660000082587895,0.9830407528599024,0.8659735544161342,0.9832758489444736,0.8659846309700315,0.9741815746301953,0.8659622570393926
+2,4000,0.9675477468116134,0.8659942201221856,0.98432340510277,0.8659730546350629,0.9838875714591936,0.8659810860092565,0.9701339007783303,0.8657348099139346
+2,6000,0.9631428719182976,0.8660086556808969,0.9875279673334031,0.8659980204701055,0.9865944839729344,0.8660032042517799,0.9680592896500297,0.8659187063028077
+2,8000,0.9739747492233086,0.8659923025529875,0.9870653841488919,0.8659751699881644,0.9872624004765722,0.8659844333828469,0.9771609807402465,0.8659248547817104
+2,10000,0.9595340015128075,0.8659705444524671,0.9875605215862908,0.8659413010671804,0.9854495726257982,0.8659595256630158,0.9646104920890192,0.8659126508090284
+2,12000,0.9633881401474407,0.86597327593827,0.9878431429577965,0.8659503087598241,0.9866889490532749,0.8659611993522207,0.96660842615623,0.86584712130582
+2,-1,0.9602841062819389,0.8659641171142265,0.9881791764986009,0.8659451366013348,0.9862481675030815,0.8659439162043878,0.9647330050743066,0.865919031743243
+3,2000,0.9738982495029145,0.8659624783829359,0.9886064323272725,0.8659614782972382,0.9882203215756932,0.8659721364312888,0.973056077003133,0.8658396013428434
+3,4000,0.9654259192987112,0.8659162197687099,0.9900150095651109,0.865936175401967,0.9879696217075965,0.8659326188156862,0.9672384492630365,0.8657297423732115
+3,6000,0.9461672497001872,0.8659386167511743,0.9883663539601071,0.8659953472185793,0.9834505717261531,0.8659870601425252,0.9508572601391017,0.8656473365141927
+3,8000,0.9629828726832148,0.8659027951936242,0.9895712303419852,0.8659947777037529,0.9870734707895225,0.8659820971949412,0.9680127613348622,0.8658359866381388

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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:857be2eac1d708b6816dd12b24770432538d3b80fbe801b723c526ad2e8759bc
+size 433312301

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}