Upload folder using huggingface_hub

README.md

@@ -85,9 +85,9 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 13 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 497 with parameters:
 ```
-{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
 **Loss**:
@@ -97,13 +97,13 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 3,
+    "epochs": 20,
     "evaluation_steps": 0,
     "evaluator": "NoneType",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
     "optimizer_params": {
-        "lr": 0.0005
+        "lr": 5e-05
     },
     "scheduler": "constantlr",
     "steps_per_epoch": null,
@@ -116,7 +116,7 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 80, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (0): Transformer({'max_seq_length': 50, '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

@@ -1,29 +1,32 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-mpnet-base-v2/",
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/facebook_mcontriever-msmarco",
   "architectures": [
-    "XLMRobertaModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
   "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": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "pooling": "average",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.30.2",
+    "pytorch": "2.0.0"
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d2045958bf953922c3ad6fbeceded5ff5c2b34d2ac00532a6f8332643d90b87
-size 1112245805
+oid sha256:88a1bf1cb90bc485eaea278df207a9e1c782b3f7188b6e298116a07becbb4fde
+size 711484973

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 80,
+  "max_seq_length": 50,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54a06c2a8b8041b979a9167588cf3adec464fb634ad3b32fbc412c8a4398303
-size 17082912
+oid sha256:340249b38ec6fcb3febeb65b596d17cdc6017ec0c7e7606ba6160562b497cec8
+size 2919614

tokenizer_config.json

@@ -1,19 +1,13 @@
 {
-  "bos_token": "<s>",
   "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
-  },
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }