Training in progress epoch 0

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: PlasmicZ/SIH3
+  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. -->
+
+# PlasmicZ/SIH3
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 3.6966
+- Validation Loss: 3.6944
+- Train Accuracy: 0.0139
+- 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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 450, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 3.6966     | 3.6944          | 0.0139         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- TensorFlow 2.17.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "India",
+    "1": "Shiv Sena",
+    "2": "knife ",
+    "3": "musician ",
+    "4": "affiliate",
+    "5": "washroom",
+    "6": "live in relationship",
+    "7": "level sign 1",
+    "8": "swing ",
+    "9": "nurse ",
+    "10": "excuse",
+    "11": "raise ",
+    "12": "dartboard",
+    "13": "update news, information",
+    "14": "4 four",
+    "15": "Huawei Mobile",
+    "16": "February",
+    "17": "pencil ",
+    "18": "proof sign 1",
+    "19": "secret ",
+    "20": "distracted",
+    "21": "bookcase, bookshelf",
+    "22": "one day cricket, 50 overs format sign and explanation",
+    "23": "greedy ",
+    "24": "Allahabad Bank",
+    "25": "form sign 1",
+    "26": "market",
+    "27": "Bengali",
+    "28": "strength",
+    "29": "truck ",
+    "30": "day",
+    "31": "Usury",
+    "32": "beetroot",
+    "33": "fry, frying",
+    "34": "accept",
+    "35": "network",
+    "36": "paste",
+    "37": "identity card ",
+    "38": "none, nothing ",
+    "39": "Peru"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "4 four": 14,
+    "Allahabad Bank": 24,
+    "Bengali": 27,
+    "February": 16,
+    "Huawei Mobile": 15,
+    "India": 0,
+    "Peru": 39,
+    "Shiv Sena": 1,
+    "Usury": 31,
+    "accept": 34,
+    "affiliate": 4,
+    "beetroot": 32,
+    "bookcase, bookshelf": 21,
+    "dartboard": 12,
+    "day": 30,
+    "distracted": 20,
+    "excuse": 10,
+    "form sign 1": 25,
+    "fry, frying": 33,
+    "greedy ": 23,
+    "identity card ": 37,
+    "knife ": 2,
+    "level sign 1": 7,
+    "live in relationship": 6,
+    "market": 26,
+    "musician ": 3,
+    "network": 35,
+    "none, nothing ": 38,
+    "nurse ": 9,
+    "one day cricket, 50 overs format sign and explanation": 22,
+    "paste": 36,
+    "pencil ": 17,
+    "proof sign 1": 18,
+    "raise ": 11,
+    "secret ": 19,
+    "strength": 28,
+    "swing ": 8,
+    "truck ": 29,
+    "update news, information": 13,
+    "washroom": 5
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.42.4",
+  "vocab_size": 30522
+}

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:ee19dc94d4a0c385ca1493e87fba3a19588863743ee166084108a4f269bc3ec2
+size 268071880

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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}