training_172e61b

README.md

@@ -85,7 +85,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 127 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 190 with parameters:
 ```
 {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -116,7 +116,7 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
   (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})
 )
 ```

config.json

@@ -1,24 +1,25 @@
 {
-  "_name_or_path": "sentence-transformers/multi-qa-distilbert-cos-v1",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-german-cased",
   "architectures": [
-    "DistilBertModel"
+    "BertModel"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cae562f81d91fa0c2573ea5009eaa13ded7a396bc8f6c04530a694472b2abf2
-size 265483293
+oid sha256:623ff250f91117b4a36819a47864c458bbc3dc3cb456112354612526c9c38648
+size 436393773

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851ca67100d372ca3ae031a6abd168f53489eebfd7d89523f35c5c9b4d372c3c
-size 711649
+oid sha256:d54bebe9160e2e5bce47d50dcad91e0fc9e1df3c41b46352ccc6bb8475c652ef
+size 726526

tokenizer_config.json

@@ -1,14 +1,14 @@
 {
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "sentence-transformers/multi-qa-distilbert-cos-v1",
+  "name_or_path": "bert-base-german-cased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }