Model save

README.md

@@ -1,11 +1,8 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: bert-large-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad dataset.
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-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: 128
 - 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

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForQuestionAnswering"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284c6b9426b3765f6469ad78efe1421fde2517b66d121ef9ca0dd30f8d866da5
-size 435640934
+oid sha256:4dec12a84bbad95fec4d0dd59676d610a9ed3361c2505b6596e91d2ebe7af049
+size 1336511590

raw_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a064e3b9ca9d2a356afedc39cf64f90f9ac72d029c3d29106910ef54aeb691
-size 775420626
+oid sha256:f17148cf060244258e6300ced0590f81dc1b3e4419e0e02562ea60239eb5cead
+size 2544552978

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc890072964ff292428e442369dd117aad7c492cdfa148ac3da433ba33bdb4b
+oid sha256:f9175e68671c44dbc0a0f1654e18adaa930e3b54f6d05e7efe6e93ec1992468d
 size 4664