Upload folder using huggingface_hub

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

@@ -0,0 +1,88 @@
+---
+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 3057 with parameters:
+```
+{'batch_size': 10, '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": 1,
+    "evaluation_steps": 400,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 0.0001
+    },
+    "scheduler": "warmuplinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 305,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, '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": "/root/.cache/torch/sentence_transformers/jhsmith_finetuning_mixed/",
+  "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": "4.35.2",
+  "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/binary_classification_evaluation_results_results.csv

@@ -0,0 +1,9 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
+0,400,0.8557986536107711,0.712531328201294,0.28438877290651826,0.27184035476718404,0.29815175097276264,0.3898671567440033,0.2867727777215104,0.8556456548347613,16.476024627685547,0.29102627664848785,0.2967644084934277,0.28550583657587547,24.510189056396484,0.2932845253648341,0.8557986536107711,0.7582442164421082,0.28438877290651826,0.27184035476718404,0.29815175097276264,1.1046563386917114,0.2868010627035612,0.8557986536107711,0.7125314474105835,0.28438877290651826,0.27184035476718404,0.29815175097276264,0.3898671567440033,0.28692984251148124
+0,800,0.8428702570379437,1.0,0.2716996099689297,0.15721826945145742,0.9995136186770428,0.35268521308898926,0.1500019182022798,0.842640758873929,0.00012805877486243844,0.2716996099689297,0.15721826945145742,0.9995136186770428,24.64952278137207,0.15078744017486995,0.842640758873929,5.8464715948503e-06,0.2716996099689297,0.15721826945145742,0.9995136186770428,1.1378178596496582,0.15035849029339948,0.8428702570379437,1.0000001192092896,0.2716996099689297,0.15721826945145742,0.9995136186770428,0.35268521308898926,0.15038981915918756
+0,1200,0.8429467564259486,1.0,0.2722436494214656,0.15767986442766907,0.9956225680933852,0.346087247133255,0.1897098741826344,0.842640758873929,0.00010429143003420904,0.2736872146118722,0.16036789297658863,0.9328793774319066,24.714378356933594,0.1896405334374167,0.842640758873929,4.751912456413265e-06,0.2722436494214656,0.15767986442766907,0.9956225680933852,1.143601894378662,0.18968782777027082,0.8427172582619339,1.0,0.2722436494214656,0.15767986442766907,0.9956225680933852,0.3460873067378998,0.1897612357006916
+0,1600,0.8429467564259486,1.0,0.2719153159113463,0.15736273834137376,0.9995136186770428,0.328864723443985,0.14089144735150053,0.8427172582619339,0.0011735885636880994,0.27188574451203384,0.1573308846036119,1.0,25.10045051574707,0.1429735777222008,0.8427172582619339,5.310723645379767e-05,0.2719153159113463,0.15736273834137376,0.9995136186770428,1.1585640907287598,0.14109712751872056,0.8428702570379437,1.0,0.27188574451203384,0.1573308846036119,1.0,0.3288617730140686,0.1408232471223858
+0,2000,0.8428702570379437,1.0,0.2720656345110493,0.157451370807168,1.0,0.391846239566803,0.14757150022184637,0.8427937576499388,0.00017429243598598987,0.2721556688066715,0.15751168313797595,1.0,23.77460479736328,0.15719735243666408,0.8427937576499388,7.854174327803776e-06,0.27213765718067506,0.15749961697563966,1.0,1.1028631925582886,0.14908931786498772,0.842640758873929,1.0000001192092896,0.27204763479986765,0.15743931388314572,1.0,0.39184626936912537,0.14718653051153777
+0,2400,0.8429467564259486,1.0,0.2718497950548724,0.15730680948737566,1.0,0.3650091290473938,0.1338660087386431,0.8428702570379437,0.00013009202666580677,0.27175350436392487,0.15725436179981633,0.9995136186770428,24.400989532470703,0.13664960875036225,0.8428702570379437,5.82129905524198e-06,0.2718497950548724,0.15730680948737566,1.0,1.1269347667694092,0.13539644330182293,0.8429467564259486,1.0,0.27173553719008264,0.15724232917591247,0.9995136186770428,0.36500951647758484,0.13407733659470913
+0,2800,0.8429467564259486,1.0,0.2716996099689297,0.15721826945145742,0.9995136186770428,0.3733765482902527,0.1364629821017202,0.8428702570379437,9.338024392491207e-05,0.2716996099689297,0.15721826945145742,0.9995136186770428,24.13287353515625,0.138090026007544,0.8428702570379437,4.227437784720678e-06,0.2716996099689297,0.15721826945145742,0.9995136186770428,1.1194851398468018,0.1372987070184668,0.8429467564259486,1.0,0.2716996099689297,0.15721826945145742,0.9995136186770428,0.3733765482902527,0.13634804704446896
+0,-1,0.8429467564259486,1.0,0.2716996099689297,0.15721826945145742,0.9995136186770428,0.37961846590042114,0.13624718847690453,0.8428702570379437,9.488363866694272e-05,0.2716996099689297,0.15721826945145742,0.9995136186770428,23.998687744140625,0.13798427053244927,0.8428702570379437,4.283218004275113e-06,0.2716996099689297,0.15721826945145742,0.9995136186770428,1.1138954162597656,0.13711481852996588,0.8427172582619339,1.0,0.2716996099689297,0.15721826945145742,0.9995136186770428,0.3796186149120331,0.13622244083367108

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e829186494b520b01029492e797220e562b82ec9838a666d74ca103326c31a
+size 437967672

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"
+  }
+]

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 250,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}