Training in progress epoch 0

README.md

@@ -1,53 +1,53 @@
----
-license: apache-2.0
-tags:
-- generated_from_keras_callback
-model-index:
-- name: roshan151/Model_output
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
-
-# roshan151/Model_output
-
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Train Loss: 3.7350
-- Validation Loss: 3.6761
-- Epoch: 0
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -989, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
-- training_precision: mixed_float16
-
-### Training results
-
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 3.7350     | 3.6761          | 0     |
-
-
-### Framework versions
-
-- Transformers 4.18.0
-- TensorFlow 2.6.0
-- Datasets 1.18.3
-- Tokenizers 0.11.0
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: roshan151/Model_output
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# roshan151/Model_output
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 3.1673
+- Validation Loss: 2.8445
+- Epoch: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -82, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 100, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.1673     | 2.8445          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.21.1
+- TensorFlow 2.8.2
+- Datasets 2.4.0
+- Tokenizers 0.12.1

config.json

@@ -1,25 +1,25 @@
-{
-  "_name_or_path": "bert-base-uncased",
-  "architectures": [
-    "BertForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "transformers_version": "4.18.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
-}
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.21.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

special_tokens_map.json

@@ -1 +1,7 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "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 sha256:2f48a20b2a32c6b38b710b8bd341ea56c532bf24fade4b56918776b76c84202c
-size 533687616
+oid sha256:fa7a19cd4e9c45fa45fd50796189bfd9d931ab174571af439ac98b829b40f475
+size 533687680

tokenizer.json

@@ -5,48 +5,48 @@
   "added_tokens": [
     {
       "id": 0,
-      "special": true,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 100,
-      "special": true,
       "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 101,
-      "special": true,
       "content": "[CLS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 102,
-      "special": true,
       "content": "[SEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 103,
-      "special": true,
       "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1 +1,14 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}