End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: huawei-noah/TinyBERT_General_4L_312D
+base_model: hadsag/TinyBERT_General_4L_312D-finetuned-squad
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # TinyBERT_General_4L_312D-finetuned-squad
 
-This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.5172
+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.
 
 ## Model description
 
@@ -41,15 +39,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3
 
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 1.869         | 1.0   | 8235  | 1.6441          |
-| 1.6291        | 2.0   | 16470 | 1.5051          |
-| 1.5225        | 3.0   | 24705 | 1.5172          |
-
-
 ### Framework versions
 
 - Transformers 4.37.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
+  "_name_or_path": "hadsag/TinyBERT_General_4L_312D-finetuned-squad",
   "architectures": [
     "BertForQuestionAnswering"
   ],

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -46,12 +46,19 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 384,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 128,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4792006185fe94104317e16958c57249006cc46cd2d858bea7ea4239666d186c
+oid sha256:7212b2c5a8a1395a2f62c850dcd4aff8c311690e61328d4ddee77be2c9d2f4f1
 size 4728