Finetuned from deepset/minilm-uncased-squad2

config.json

@@ -1,30 +1,25 @@
 {
-  "_name_or_path": "./unchecked-v1",
+  "_name_or_path": "deepset/minilm-uncased-squad2",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "language": "english",
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "name": "XLMRoberta",
+  "intermediate_size": 1536,
+  "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,
   "position_embedding_type": "absolute",
   "transformers_version": "4.24.0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960f82af223989171fb330e8f7741c5f69141df43950b5e81e4e5e9344805768
-size 1112470336
+oid sha256:7d7e1c920890824e816b9b19ad41ad9f674ff7dcaa1a4b25349897523120aa9e
+size 133748192

tokenizer/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "deepset/minilm-uncased-squad2",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json → tokenizer/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aab93ae54dfb8fb7fe5377a56363a237b31130bf191f57e3bd57e58e3eca760
-size 17082758
+oid sha256:c571f1b1973291370192db62060efdfb564c9a11865c568693ac7420e857cf55
+size 711494

tokenizer/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "max_len": 384,
+  "name_or_path": "deepset/minilm-uncased-squad2",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,22 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "max_len": 128,
-  "model_max_length": 512,
-  "name_or_path": "deepset/xlm-roberta-base-squad2-distilled",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
-}

training.json

@@ -0,0 +1,12 @@
+{
+    "epochs": 2,
+    "learning_rate": 1e-05,
+    "model_name": "deepset/minilm-uncased-squad2",
+    "evaluation": [
+        0.03355833771390371,
+        0.036146737329307954,
+        0.9521034393207527,
+        0.9619200527368064,
+        0.03936894991757511
+    ]
+}