Upload folder using huggingface_hub

.ipynb_checkpoints/similarity_evaluation_sts-test_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
+-1,-1,0.6744054047228356,0.6750742998718,0.6631685565159673,0.6599136568909711,0.6595100643715024,0.6593615183588794,0.666057660517302,0.6624310997086206

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,126 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+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')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_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 75 with parameters:
+```
+{'batch_size': 16, '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": 20,
+    "evaluation_steps": 1000,
+    "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": 150,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 50264,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "Ngram_size": 32768,
+  "_name_or_path": "/home/ec2-user/.cache/torch/sentence_transformers/Kyleiwaniec_COS_TAPT_n_RoBERTa",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "block_size": 128,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_Ngram_layers": 1,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.34.0",
+    "pytorch": "2.1.0+cu121"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.49697139329954926,0.4825046992439753,0.5041840862236489,0.4898646503143872,0.5298679941066685,0.5194756162488348,0.415232268926104,0.4012029141638448
+1,-1,0.6105816053705728,0.6259381642906058,0.6119457802391968,0.6329557920554172,0.6216162521489205,0.6310730138746142,0.5298615694784903,0.5316280935976543
+2,-1,0.627889232743929,0.6257670026378056,0.6088617878512252,0.6158396267753897,0.6117585196426631,0.6158396267753897,0.5946381291534514,0.599236946453763
+3,-1,0.5923863787111332,0.5997504314121638,0.5963591518282073,0.5937597735641542,0.6133336786211053,0.6124163937193842,0.5698021861330682,0.576814769936927
+4,-1,0.6403088516181896,0.6408292280842298,0.6265897721841569,0.6233707394986018,0.6064451645768036,0.6062545742185742,0.6236893460206414,0.6226860928874007
+5,-1,0.659583201557967,0.661368626420263,0.6454566441020214,0.6379194799866251,0.6454343114639428,0.645964077668238,0.6318123254688842,0.6363790251114226
+6,-1,0.658270068736161,0.6560626151834543,0.6438323301276886,0.6356943785002216,0.642272433692988,0.642198521306632,0.6443502760756001,0.6461352393210383
+7,-1,0.65964373749155,0.6586300399754584,0.6480286720463401,0.6461352393210383,0.6397026533182658,0.6425408446122326,0.6499632425608111,0.6485315024602422
+8,-1,0.6724810081502879,0.677628983436289,0.6626618661312407,0.6630802429482655,0.6478148041481298,0.6449371077514364,0.6568768022655576,0.6642783745178674
+9,-1,0.6571687288681491,0.658287716669858,0.653892509091242,0.6481891791546417,0.6423099987021536,0.6408292280842298,0.6435865611351708,0.6495584723770439
+10,-1,0.6650969725173421,0.669584385754676,0.6590824141104659,0.6545221603082518,0.6430952496897081,0.6392887732090273,0.651594735579449,0.6487026641130424
+11,-1,0.6577548003109057,0.6634225662538661,0.6539465538638317,0.6456217543626375,0.6417369524914643,0.6372348333754241,0.6441428351445646,0.6449371077514364
+12,-1,0.6495604678681547,0.645964077668238,0.6397059044066449,0.6350097318890205,0.6328643706846068,0.6300460439578125,0.6406441339960222,0.6408292280842298
+13,-1,0.6557075046885295,0.6546933219610521,0.6472685513761665,0.6394599348618276,0.6364113875396769,0.6336404386666183,0.6500737668697025,0.6519547355162477
+14,-1,0.6611204239050532,0.6565761001418552,0.6520045144594881,0.6475045325434405,0.6401604331914832,0.6387752882506266,0.6554753492516101,0.6562337768362545
+15,-1,0.6547453773324794,0.6564049384890548,0.6456277421569683,0.6432254912234336,0.6329786733946647,0.6351808935418207,0.6475071089006532,0.64716220923784
+16,-1,0.6546015024673933,0.6552068069194529,0.6465170171910348,0.6420273596538317,0.6356710916166742,0.6368925100698235,0.6481358682068578,0.6476756941962408
+17,-1,0.6562048442441608,0.6557202918778537,0.6460790408264685,0.6396310965146279,0.6345839539300447,0.63466740858342,0.6510543316716926,0.6500719573354447
+18,-1,0.6557946409978526,0.6550356452666526,0.6459793778969569,0.6399734198202285,0.63437400947207,0.6332981153610178,0.650419573877459,0.6526393821274488
+19,-1,0.6561024474465611,0.6570895851002561,0.6464077494746332,0.641513874695431,0.6352225969057199,0.6355232168474213,0.6508822963387766,0.6514412505578469

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3071ca5c5cafe3686ead39447abf20cfcc558fb1f99045241828d5a8f774dc
+size 1421571238

sentence_bert_config.json

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

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.6744054047228356,0.6750742998718,0.6631685565159673,0.6599136568909711,0.6595100643715024,0.6593615183588794,0.666057660517302,0.6624310997086206

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "Ngram_vocab_size": 32768,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}