Add new SentenceTransformer model.

1_Pooling/config.json

@@ -5,6 +5,5 @@
   "pooling_mode_max_tokens": false,
   "pooling_mode_mean_sqrt_len_tokens": false,
   "pooling_mode_weightedmean_tokens": false,
-  "pooling_mode_lasttoken": false,
-  "include_prompt": true
+  "pooling_mode_lasttoken": false
 }

README.md

@@ -7,7 +7,7 @@ tags:
 - sentence-similarity
 - transformers
 datasets:
-- embedding-data/QQP_triplets
+- embedding-data/sentence-compression
 ---
 
 # arjunsama/mine
@@ -82,12 +82,47 @@ print(sentence_embeddings)
 For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=arjunsama/mine)
 
 
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 5469 with parameters:
+```
+{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 0,
+    "evaluator": "NoneType",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 5469,
+    "weight_decay": 0.01
+}
+```
+
 
 ## Full Model Architecture
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
 )
 ```
 

config.json

@@ -1,30 +1,25 @@
 {
-  "_name_or_path": "avsolatorio/GIST-small-Embedding-v0",
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 384,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 1536,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.37.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

config_sentence_transformers.json

@@ -1,9 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.5.1",
-    "transformers": "4.38.1",
-    "pytorch": "2.1.0+cu121"
-  },
-  "prompts": {},
-  "default_prompt_name": null
+    "sentence_transformers": "2.3.1",
+    "transformers": "4.37.2",
+    "pytorch": "2.2.0+cu121"
+  }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa751a822b7eb0a7db5d0167b6e38ffd6ad1978e71de205d7c0efedcc18bf2a
-size 133462128
+oid sha256:53cfb0a5e78786bcb47155c5cfba736d0eaff820dbee765bcab62dfdde852f16
+size 90864192

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -46,12 +46,19 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 128,
   "model_max_length": 512,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }