Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: Intel/dynamic_tinybert
+license: cc-by-4.0
+base_model: deepset/minilm-uncased-squad2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # StaAhmed/Model_QA
 
-This model is a fine-tuned version of [Intel/dynamic_tinybert](https://huggingface.co/Intel/dynamic_tinybert) on an unknown dataset.
+This model is a fine-tuned version of [deepset/minilm-uncased-squad2](https://huggingface.co/deepset/minilm-uncased-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.9576
-- Epoch: 3
+- Train Loss: 4.6071
+- Epoch: 0
 
 ## Model description
 
@@ -42,10 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 5.9561     | 0     |
-| 5.9592     | 1     |
-| 5.9634     | 2     |
-| 5.9576     | 3     |
+| 4.6071     | 0     |
 
 
 ### Framework versions

config.json

@@ -1,27 +1,23 @@
 {
-  "_name_or_path": "Intel/dynamic_tinybert",
+  "_name_or_path": "deepset/minilm-uncased-squad2",
   "architectures": [
     "BertForQuestionAnswering"
   ],
-  "attention_head_size": 26,
   "attention_probs_dropout_prob": 0.1,
-  "cell": {},
   "classifier_dropout": null,
   "gradient_checkpointing": false,
-  "hidden_act": "relu",
+  "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "pre_trained": "",
-  "structure": [],
   "transformers_version": "4.37.2",
   "type_vocab_size": 2,
   "use_cache": true,

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "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
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e7782d768d5a5a9e41edafb88260cbac1b23d6d3f0b11082fdbc6cb9c615aa
-size 265609448
+oid sha256:9e421c7cfc7af379cb536930ef29653cc626a94a51f71a35b96ba3d173bf45a8
+size 133136632

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "full_tokenizer_file": null,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,