Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: timpal0l/mdeberta-v3-base-squad2
+license: apache-2.0
+base_model: Intel/dynamic_tinybert
 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 [Intel/dynamic_tinybert](https://huggingface.co/Intel/dynamic_tinybert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.4553
+- Train Loss: 3.9951
 - Epoch: 0
 
 ## Model description
@@ -42,12 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 3.4553     | 0     |
+| 3.9951     | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.37.2
 - TensorFlow 2.15.0
-- Datasets 2.17.0
-- Tokenizers 0.15.1
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -1,35 +1,29 @@
 {
-  "_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
+  "_name_or_path": "Intel/dynamic_tinybert",
   "architectures": [
-    "DebertaV2ForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
+  "attention_head_size": 26,
   "attention_probs_dropout_prob": 0.1,
-  "hidden_act": "gelu",
+  "cell": {},
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "relu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-07,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "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
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "structure": [],
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

special_tokens_map.json

@@ -1,9 +1,37 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "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
+  }
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc5ce905a0d2519fbc32876fefa53af6b20fa47c42d5e56f3acb5647e5e839d
-size 1113165584
+oid sha256:6b882c42a0804de1c8a4d9d699df16b235e1911e6f9fb3ce64e1079f81541a7c
+size 265609448

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1138eab70286f87e95bdf1fb4f1f173698ab5b130389032f399ea67b917bd07
-size 16316412
+oid sha256:7e584a910b73d688ab7251fdc120d33bf7d717025d271b50029ea9058e8ca407
+size 711659

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[CLS]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "[SEP]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250101": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,18 +41,17 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }