End of training

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: hadsag/TinyBERT_General_4L_312D-finetuned-squad
+license: apache-2.0
+base_model: kaporter/bert-base-uncased-finetuned-squad
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # TinyBERT_General_4L_312D-finetuned-squad
 
-This model is a fine-tuned version of [hadsag/TinyBERT_General_4L_312D-finetuned-squad](https://huggingface.co/hadsag/TinyBERT_General_4L_312D-finetuned-squad) on an unknown dataset.
+This model is a fine-tuned version of [kaporter/bert-base-uncased-finetuned-squad](https://huggingface.co/kaporter/bert-base-uncased-finetuned-squad) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,26 +1,23 @@
 {
-  "_name_or_path": "hadsag/TinyBERT_General_4L_312D-finetuned-squad",
+  "_name_or_path": "kaporter/bert-base-uncased-finetuned-squad",
   "architectures": [
     "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "cell": {},
   "classifier_dropout": null,
-  "emb_size": 312,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 312,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1200,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 4,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "pre_trained": "",
-  "structure": [],
   "torch_dtype": "float32",
   "transformers_version": "4.37.2",
   "type_vocab_size": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e315d8533371570ebe7d4439e57411e8544cde1e55be394b3408d7c2b6a98b12
-size 57020992
+oid sha256:ef815efb9ad760f78327b9ee90e2dc29943b61af9278af99a218d782f458d763
+size 435596088

tokenizer_config.json

@@ -43,12 +43,10 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "max_length": 384,
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
   "pad_token_type_id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7212b2c5a8a1395a2f62c850dcd4aff8c311690e61328d4ddee77be2c9d2f4f1
+oid sha256:34d9571cdc24a11c438819b53b0d3828ace48cd472ac2d694bad5d9a6348f784
 size 4728