Training in progress epoch 0

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: twmkn9/albert-base-v2-squad2
+license: mit
+base_model: csarron/mobilebert-uncased-squad-v2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/mobilebert-uncased-finetuned-agic-031223
 
-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.
+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.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1807
+- Train Loss: 2.8297
 - Validation Loss: 0.0
-- Epoch: 14
+- Epoch: 0
 
 ## Model description
 
@@ -35,28 +36,14 @@ 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': 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}
+- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 1725, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.7349     | 0.0             | 0     |
-| 1.9998     | 0.0             | 1     |
-| 1.5750     | 0.0             | 2     |
-| 1.2249     | 0.0             | 3     |
-| 0.9387     | 0.0             | 4     |
-| 0.7156     | 0.0             | 5     |
-| 0.5497     | 0.0             | 6     |
-| 0.4392     | 0.0             | 7     |
-| 0.3686     | 0.0             | 8     |
-| 0.3066     | 0.0             | 9     |
-| 0.2670     | 0.0             | 10    |
-| 0.2375     | 0.0             | 11    |
-| 0.2141     | 0.0             | 12    |
-| 0.1966     | 0.0             | 13    |
-| 0.1807     | 0.0             | 14    |
+| 2.8297     | 0.0             | 0     |
 
 
 ### Framework versions

config.json

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

special_tokens_map.json

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

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007ce6aaa2834e6e6e2540f1736ff882f841556c830a1207333e695357e976a2
-size 44417688
+oid sha256:f23afd3be7223edd33da9ffc3684c3e14fd509e78216bf08fee300bae9181fe2
+size 99822192

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