Training in progress epoch 0

README.md

@@ -1,6 +1,5 @@
 ---
-license: mit
-base_model: csarron/mobilebert-uncased-squad-v2
+base_model: twmkn9/albert-base-v2-squad2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/mobilebert-uncased-finetuned-agic-031223
 
-This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v2](https://huggingface.co/csarron/mobilebert-uncased-squad-v2) on an unknown dataset.
+This model is a fine-tuned version of [twmkn9/albert-base-v2-squad2](https://huggingface.co/twmkn9/albert-base-v2-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0000
+- Train Loss: 2.7349
 - Validation Loss: 0.0
-- Epoch: 2
+- Epoch: 0
 
 ## Model description
 
@@ -36,21 +35,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 912, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 2265, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.0000     | 0.0             | 0     |
-| 0.0000     | 0.0             | 1     |
-| 0.0000     | 0.0             | 2     |
+| 2.7349     | 0.0             | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- TensorFlow 2.14.0
-- Datasets 2.15.0
+- TensorFlow 2.15.0
+- Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -1,32 +1,33 @@
 {
-  "_name_or_path": "csarron/mobilebert-uncased-squad-v2",
+  "_name_or_path": "twmkn9/albert-base-v2-squad2",
   "architectures": [
-    "MobileBertForQuestionAnswering"
+    "AlbertForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_activation": false,
-  "classifier_dropout": null,
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
   "embedding_size": 128,
-  "hidden_act": "relu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 512,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "intra_bottleneck_size": 128,
-  "key_query_shared_bottleneck": true,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "mobilebert",
-  "normalization_type": "no_norm",
-  "num_attention_heads": 4,
-  "num_feedforward_networks": 4,
-  "num_hidden_layers": 24,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "output_past": true,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "transformers_version": "4.35.2",
-  "trigram_input": true,
-  "true_hidden_size": 128,
   "type_vocab_size": 2,
-  "use_bottleneck": true,
-  "use_bottleneck_attention": false,
-  "vocab_size": 30522
+  "vocab_size": 30000
 }

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f961d75dcde5f3a3a1fa8d104e50b67d44071de3557dc4059c872293ce07279
-size 99822192
+oid sha256:a923d5fbb954928ed12cc17cef09664cd85fbf7b2a8c6995230d882a7eda294e
+size 44417688

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,27 +32,28 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
-  "full_tokenizer_file": null,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "MobileBertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }