add initial version - 10 ep

fine_tune_10/1_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
+}

fine_tune_10/README.md

@@ -0,0 +1,87 @@
+---
+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 570 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": 10,
+    "evaluation_steps": 1000,
+    "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": 570,
+    "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 -->

fine_tune_10/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/home/marcos/.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": "4.17.0",
+  "vocab_size": 30527
+}

fine_tune_10/config_sentence_transformers.json

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

fine_tune_10/eval/similarity_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.6305194317299957,0.8999999999999998,0.6448546766475179,0.8999999999999998,0.6088612748562449,0.7,0.630520367778926,0.8999999999999998
+1,-1,0.6502821024160134,0.7,0.6767093296654189,0.7,0.6401415629871852,0.7,0.6502828829688981,0.7
+2,-1,0.7044981032334714,0.7,0.7209636478993264,0.7,0.6860280041008808,0.7,0.7044981510534786,0.7
+3,-1,0.7268506333698956,0.7,0.7427746517109477,0.7,0.7155316384927595,0.7,0.7268506234110871,0.7
+4,-1,0.8434477171174481,0.8999999999999998,0.8413084907749916,0.8999999999999998,0.8247787966338731,0.8999999999999998,0.8434477017214883,0.8999999999999998
+5,-1,0.8550643497106197,0.8999999999999998,0.85193411644713,0.8999999999999998,0.8373358707378502,0.8999999999999998,0.8550645269733299,0.8999999999999998
+6,-1,0.8665102964470229,0.8999999999999998,0.8629390316822539,0.8999999999999998,0.8549897542060918,0.8999999999999998,0.8665105276537461,0.8999999999999998
+7,-1,0.898872607635995,0.8999999999999998,0.8914694685220438,0.8999999999999998,0.8804262339108858,0.8999999999999998,0.8988723863177053,0.8999999999999998
+8,-1,0.8934154608933851,0.8999999999999998,0.8859234332918398,0.8999999999999998,0.8727800276506579,0.8999999999999998,0.8934149874256542,0.8999999999999998
+9,-1,0.900000828015698,0.8999999999999998,0.8915260803610613,0.8999999999999998,0.8808519462404801,0.8999999999999998,0.900000725679198,0.8999999999999998

fine_tune_10/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"
+  }
+]

fine_tune_10/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a68c4006656f66058ef1fa0480192226edf938ee590fa1e0bc26cadd46b95ad
+size 438023729

fine_tune_10/sentence_bert_config.json

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

fine_tune_10/special_tokens_map.json

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

fine_tune_10/tokenizer_config.json

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