Update model with new data

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 128,
+  "word_embedding_dimension": 256,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

README.md

@@ -7,9 +7,9 @@ tags:
 - transformers
 ---
 
-# {MODEL_NAME}
+# bert-base-dutch-cased-snli
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 128 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 256 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -27,7 +27,7 @@ Then you can use the model like this:
 from sentence_transformers import SentenceTransformer
 sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('bert-base-dutch-cased-snli')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -53,8 +53,8 @@ def mean_pooling(model_output, attention_mask):
 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}')
+tokenizer = AutoTokenizer.from_pretrained('bert-base-dutch-cased-snli')
+model = AutoModel.from_pretrained('bert-base-dutch-cased-snli')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -76,7 +76,7 @@ print(sentence_embeddings)
 
 <!--- 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})
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=bert-base-dutch-cased-snli)
 
 
 ## Training
@@ -84,7 +84,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 559 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 339 with parameters:
 ```
 {'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -100,17 +100,17 @@ Parameters of the fit()-Method:
 ```
 {
     "callback": null,
-    "epochs": 3,
+    "epochs": 1,
     "evaluation_steps": 0,
-    "evaluator": "NoneType",
+    "evaluator": "utils.CombEvaluator",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'transformers.optimization.AdamW'>",
     "optimizer_params": {
-        "lr": 1.25e-05
+        "lr": 2e-05
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
-    "warmup_steps": 336,
+    "warmup_steps": 10000,
     "weight_decay": 0.01
 }
 ```
@@ -120,7 +120,7 @@ Parameters of the fit()-Method:
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 128, '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': 256, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
 )
 ```
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "GroNLP/bert-base-dutch-cased",
+  "_name_or_path": "./bert-base-dutch-cased-snli/",
   "architectures": [
     "BertModel"
   ],
@@ -17,7 +17,8 @@
   "num_hidden_layers": 12,
   "pad_token_id": 3,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.8.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30073

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.0.0",
-    "transformers": "4.8.1",
-    "pytorch": "1.6.0"
+    "transformers": "4.9.1",
+    "pytorch": "1.9.0+cu102"
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a58ecac26466378a622f286b45c08dcd9e7ce5bc35b153d3de5208b50db90a6c
-size 436634197
+oid sha256:52b03cd6620d16ba1ed4f3d7b9ff94c8104284f3daa9b80f024f4419e5bede58
+size 436630961

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/adb82a117c09b0f8768357de8e836a9e0610730782f82edc49dd0020c48f1d03.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "GroNLP/bert-base-dutch-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/adb82a117c09b0f8768357de8e836a9e0610730782f82edc49dd0020c48f1d03.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "./bert-base-dutch-cased-snli/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}