Modified validation and training for linktransformer model

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 .git/lfs/objects/a9/a3/a9a34a666447dbbd0b4be8ba7865bf6748abd81f63dcb52668c47681cbe29c03 filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/48/8a/488aa4746aae10652265c4f48d8ddaaf8e302e6fbd4a5db9da494309eaa8eeac filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -3,5 +3,7 @@
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,
-  "pooling_mode_mean_sqrt_len_tokens": false
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
 }

LT_training_config.json

@@ -6,7 +6,8 @@
   "train_batch_size": 64,
   "num_epochs": 100,
   "warm_up_perc": 1,
-  "learning_rate": 2e-06,
+  "learning_rate": 2e-05,
+  "loss_type": "supcon",
   "val_perc": 0.2,
   "wandb_names": {
     "project": "linkage",
@@ -16,9 +17,11 @@
   },
   "add_pooling_layer": false,
   "large_val": true,
-  "eval_steps_perc": 0.1,
+  "eval_steps_perc": 0.5,
   "test_at_end": true,
   "save_val_test_pickles": true,
+  "val_query_prop": 0.5,
+  "loss_params": {},
   "eval_type": "retrieval",
   "training_dataset": "dataframe",
   "base_model_path": "dangvantuan/sentence-camembert-large",

README.md

@@ -12,7 +12,7 @@ tags:
 
 # dell-research-harvard/lt-wikidata-comp-fr
 
-This is a [LinkTransformer](https://github.com/dell-research-harvard/linktransformer) model. At its core this model this is a sentence transformer model [sentence-transformers](https://www.SBERT.net) model- it just wraps around the class. 
+This is a [LinkTransformer](https://linktransformer.github.io/) model. At its core this model this is a sentence transformer model [sentence-transformers](https://www.SBERT.net) model- it just wraps around the class. 
 It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more.
 Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. 
 It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
@@ -97,7 +97,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 279 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 664 with parameters:
 ```
 {'batch_size': 64, 'sampler': 'torch.utils.data.dataloader._InfiniteConstantSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -110,16 +110,16 @@ Parameters of the fit()-Method:
 ```
 {
     "epochs": 100,
-    "evaluation_steps": 2790,
+    "evaluation_steps": 332,
     "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
     "optimizer_params": {
-        "lr": 2e-06
+        "lr": 2e-05
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
-    "warmup_steps": 27900,
+    "warmup_steps": 66400,
     "weight_decay": 0.01
 }
 ```
@@ -129,10 +129,20 @@ Parameters of the fit()-Method:
 
 LinkTransformer(
   (0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: CamembertModel 
-  (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})
+  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
 )
 ```
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->
+```
+@misc{arora2023linktransformer,
+                  title={LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models},
+                  author={Abhishek Arora and Melissa Dell},
+                  year={2023},
+                  eprint={2309.00789},
+                  archivePrefix={arXiv},
+                  primaryClass={cs.CL}
+                }
+
+```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/linkage_fr_aliases/",
+  "_name_or_path": "models/linkage_fr_aliases",
   "architectures": [
     "CamembertModel"
   ],
@@ -22,7 +22,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.35.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 32005

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.2.2",
-    "transformers": "4.31.0",
-    "pytorch": "2.0.1+cu117"
+    "sentence_transformers": "2.3.1",
+    "transformers": "4.35.1",
+    "pytorch": "2.1.0+cu121"
   }
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a56826146b5cb12d144aa0b713be15bf0a64b42901cd7dc202a9d0bce6af49
+size 1346690896

special_tokens_map.json

@@ -3,9 +3,27 @@
     "<s>NOTUSED",
     "</s>NOTUSED"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "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,
@@ -13,7 +31,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "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.json

@@ -128210,6 +128210,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,4 +1,62 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<s>NOTUSED",
     "</s>NOTUSED"
@@ -7,18 +65,18 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
+  "max_length": 514,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "CamembertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }