Model save

README.md

@@ -1,11 +1,8 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: bert-base-uncased
 tags:
-- question-answering
 - generated_from_trainer
-datasets:
-- squad
 model-index:
 - name: out
   results: []
@@ -16,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 
 ## Model description
 
@@ -36,12 +33,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
+- train_batch_size: 256
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 100.0
+- num_epochs: 3.0
 
 ### Training results
 

config.json

@@ -1,24 +1,26 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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": "4.35.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:178ca09ca07d2ec3563210faacf111b1b01d3f8da3762c2880bd9c156ab4afac
-size 265493026
+oid sha256:07ea90ed30df521e24332520fe788621f90f309c9652eb0f37dc7cd25c607603
+size 435640934

raw_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035b7c535cddf8591e845594d6ea6280ac24f6518254898eb5cb325b5fca5405
-size 435382250
+oid sha256:3553b4645a612e626847f4f49a24ac2e8a37a1bccceef94d7c94d538807e8f96
+size 775420626

tokenizer_config.json

@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875493d1acde876206cc9780a2c8990fbe6691b70be59c12fd6bd40a0718bf6e
+oid sha256:3393d1f4d3f2362c9a05b6ed8fb76de9a41bf4fd82be6a0b62209ddbcec2511c
 size 4664