Training in progress epoch 0

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Sanyam52/bert-pos-tagging
+  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. -->
+
+# Sanyam52/bert-pos-tagging
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.4190
+- Validation Loss: 1.2434
+- 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': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1634, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, '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 |
+|:----------:|:---------------:|:-----:|
+| 2.4190     | 1.2434          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- TensorFlow 2.17.0
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,123 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\"",
+    "1": "''",
+    "2": "#",
+    "3": "$",
+    "4": "(",
+    "5": ")",
+    "6": ",",
+    "7": ".",
+    "8": ":",
+    "9": "``",
+    "10": "CC",
+    "11": "CD",
+    "12": "DT",
+    "13": "EX",
+    "14": "FW",
+    "15": "IN",
+    "16": "JJ",
+    "17": "JJR",
+    "18": "JJS",
+    "19": "LS",
+    "20": "MD",
+    "21": "NN",
+    "22": "NNP",
+    "23": "NNPS",
+    "24": "NNS",
+    "25": "NN|SYM",
+    "26": "PDT",
+    "27": "POS",
+    "28": "PRP",
+    "29": "PRP$",
+    "30": "RB",
+    "31": "RBR",
+    "32": "RBS",
+    "33": "RP",
+    "34": "SYM",
+    "35": "TO",
+    "36": "UH",
+    "37": "VB",
+    "38": "VBD",
+    "39": "VBG",
+    "40": "VBN",
+    "41": "VBP",
+    "42": "VBZ",
+    "43": "WDT",
+    "44": "WP",
+    "45": "WP$",
+    "46": "WRB"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\"": 0,
+    "#": 2,
+    "$": 3,
+    "''": 1,
+    "(": 4,
+    ")": 5,
+    ",": 6,
+    ".": 7,
+    ":": 8,
+    "CC": 10,
+    "CD": 11,
+    "DT": 12,
+    "EX": 13,
+    "FW": 14,
+    "IN": 15,
+    "JJ": 16,
+    "JJR": 17,
+    "JJS": 18,
+    "LS": 19,
+    "MD": 20,
+    "NN": 21,
+    "NNP": 22,
+    "NNPS": 23,
+    "NNS": 24,
+    "NN|SYM": 25,
+    "PDT": 26,
+    "POS": 27,
+    "PRP": 28,
+    "PRP$": 29,
+    "RB": 30,
+    "RBR": 31,
+    "RBS": 32,
+    "RP": 33,
+    "SYM": 34,
+    "TO": 35,
+    "UH": 36,
+    "VB": 37,
+    "VBD": 38,
+    "VBG": 39,
+    "VBN": 40,
+    "VBP": 41,
+    "VBZ": 42,
+    "WDT": 43,
+    "WP": 44,
+    "WP$": 45,
+    "WRB": 46,
+    "``": 9
+  },
+  "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": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e538de4d8aeeac2b08595dd3721035ecad8917a825e99e8aca355c559a63aef4
+size 431296644

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}