Updated BERT classifier on augmented of smaller classes

config.json

@@ -0,0 +1,219 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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": "crop_pest_pest/disease - symptom",
+    "1": "crop_seed_seed - varieties",
+    "2": "crop_cultivation timelines",
+    "3": "scheme_scheme - info",
+    "4": "scheme_price",
+    "5": "crop_pest_pest/disease - control",
+    "6": "crop_weed_weed - control",
+    "7": "crop_sowing method",
+    "8": "crop_fertilizer_fertilizer - application",
+    "9": "crop_pest_pest/disease - prevention",
+    "10": "crop",
+    "11": "crop_organic methods",
+    "12": "non-agri",
+    "13": "crop_fertilizer",
+    "14": "crop_weed",
+    "15": "scheme",
+    "16": "crop_harvesting methods",
+    "17": "scheme_scheme - grievance",
+    "18": "crop_irrigation",
+    "19": "crop_weed_weed - prevention",
+    "20": "crop_description/profile",
+    "21": "crop_seed_seed - protection",
+    "22": "crop_weed - control",
+    "23": "crop_pest_pest/disease - procurement",
+    "24": "crop_seed_seed - procurement",
+    "25": "crop_seed ",
+    "26": "crop_crop use cases",
+    "27": "crop_fertilizer_seed - varieties",
+    "28": "crop_profile",
+    "29": "crop_cultivation",
+    "30": "crop_pest",
+    "31": "machinery_machinery - procurement",
+    "32": "scheme_scheme - application/registration",
+    "33": "scheme_scheme - eligibility",
+    "34": "crop_transplantation",
+    "35": "crop_fertilizer_fertilizer - description/profile",
+    "36": "crop_seed_seed - rate",
+    "37": "crop_soil_soil health",
+    "38": "crop_seed",
+    "39": "crop_soil_soil preparation",
+    "40": "crop_cultivation ",
+    "41": "crop_weed_weed - symptom",
+    "42": "crop_food processing",
+    "43": "crop_intercropping",
+    "44": "crop_storage",
+    "45": "scheme_scheme - notifications",
+    "46": "scheme_scheme - documents required",
+    "47": "crop_fertilizer_pest/disease - control",
+    "48": "crop_price",
+    "49": "crop_pest_fertilizer - application",
+    "50": "machinery_machinery - info",
+    "51": "non-agri_fertilizer - application",
+    "52": "crop_seed_pest/disease - control",
+    "53": "crop_pest_seed - varieties",
+    "54": "machinery_machinery - usage",
+    "55": "crop_scheme - info",
+    "56": "scheme_fertilizer_fertilizer - application",
+    "57": "crop_pest_pest/disease - level of infestation",
+    "58": "crop_fertilizer_fertilizer - procurement",
+    "59": "crop_machinery - procurement",
+    "60": "scheme_description/profile",
+    "61": "crop_pest_pest control",
+    "62": "crop_pest_pest/disease - info",
+    "63": "crop_soil_soil - info",
+    "64": "non-agri_weather",
+    "65": "crop_yield",
+    "66": "crop_weather",
+    "67": "crop_pest_pest/disease - pesticide info",
+    "68": "crop_soil",
+    "69": "crop_pest_pest/disease - biological control",
+    "70": "crop_junk",
+    "71": "non-agri_junk",
+    "72": "crop_organic methods_pest/disease - control",
+    "73": "crop_pest/disease - pesticide info",
+    "74": "crop_income",
+    "75": "crop_seed_seed - storage",
+    "76": "scheme_scheme - info_pest/disease - control",
+    "77": "crop_agricultural statistics",
+    "78": "crop_pest_agricultural statistics",
+    "79": "crop_pest_junk",
+    "80": "scheme_junk",
+    "81": "crop_pest_ pest/disease - info",
+    "82": "crop_pest_yield",
+    "83": "non-agri_cultivation timelines",
+    "84": "crop_pest/disease - info",
+    "85": "machinery",
+    "86": "crop_description/profile_junk",
+    "87": "machinery_machinery - info_junk",
+    "88": "scheme_scheme - info_junk",
+    "89": "crop_animal husbandry",
+    "90": "crop_fishery",
+    "91": "crop_junki",
+    "92": "crop_fertilizer_pest/disease - biological control",
+    "93": "crop_description/profile_animal husbandry"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed0bc249faffcd4a58de1f5097b2ced77c5196b7139be3c075ebb7bb21ceeb2
+size 279183360

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}