Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: timpal0l/mdeberta-v3-base-squad2
+base_model: microsoft/deberta-v3-base
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 # StaAhmed/Model_QA
 
-This model is a fine-tuned version of [timpal0l/mdeberta-v3-base-squad2](https://huggingface.co/timpal0l/mdeberta-v3-base-squad2) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.6107
+- Train Loss: 3.4110
 - Epoch: 0
 
 ## Model description
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 2.6107     | 0     |
+| 3.4110     | 0     |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
     "DebertaV2ForQuestionAnswering"
   ],
@@ -28,8 +28,7 @@
   "position_buckets": 256,
   "relative_attention": true,
   "share_att_key": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "type_vocab_size": 0,
-  "vocab_size": 251000
+  "vocab_size": 128100
 }

special_tokens_map.json

@@ -5,5 +5,11 @@
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39350c9682d299178e833e9bfb065d73ba8de5f290ba94d9f7d8c88838e85c21
-size 1113165584
+oid sha256:296b82fd9c2bc6caeedaaecbb909e6edcec0558ee9b0111e5c213ce782843322
+size 735616784

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1138eab70286f87e95bdf1fb4f1f173698ab5b130389032f399ea67b917bd07
-size 16316412
+oid sha256:9dd512217a44e58e6d5782dc9540daad7615c7217f25e7706a22cccf9df7e1d6
+size 8656909

tokenizer_config.json

@@ -27,12 +27,12 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250101": {
+    "128000": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,