sandip404/sambodhan-nepali-grievance-muril

README.md

@@ -1,73 +1,70 @@
----
-library_name: transformers
-license: apache-2.0
-base_model: google/muril-base-cased
-tags:
-- generated_from_trainer
-metrics:
-- accuracy
-- f1
-- precision
-- recall
-model-index:
-- name: results
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# results
-
-This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.8392
-- Accuracy: 0.8555
-- F1: 0.8560
-- Precision: 0.8600
-- Recall: 0.8555
-
-## 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:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 5
-- mixed_precision_training: Native AMP
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 1.546         | 1.0   | 170  | 1.4365          | 0.4322   | 0.3232 | 0.3692    | 0.4322 |
-| 1.2151        | 2.0   | 340  | 1.1372          | 0.5339   | 0.4345 | 0.4263    | 0.5339 |
-| 0.9865        | 3.0   | 510  | 0.9491          | 0.7080   | 0.6423 | 0.6121    | 0.7080 |
-| 0.8873        | 4.0   | 680  | 0.8685          | 0.7611   | 0.7264 | 0.8391    | 0.7611 |
-| 0.8119        | 5.0   | 850  | 0.8392          | 0.8555   | 0.8560 | 0.8600    | 0.8555 |
-
-
-### Framework versions
-
-- Transformers 4.57.0
-- Pytorch 2.8.0+cu126
-- Datasets 4.0.0
-- Tokenizers 0.22.1
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/muril-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8564
+- Accuracy: 0.8761
+- F1: 0.8755
+- Precision: 0.8892
+- Recall: 0.8761
+
+## 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:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.3029        | 1.0   | 339  | 1.1999          | 0.5634   | 0.4575 | 0.4881    | 0.5634 |
+| 1.0073        | 2.0   | 678  | 0.9380          | 0.7168   | 0.6836 | 0.7627    | 0.7168 |
+| 0.8519        | 3.0   | 1017 | 0.8564          | 0.8761   | 0.8755 | 0.8892    | 0.8761 |
+
+
+### Framework versions
+
+- Transformers 4.56.2
+- Pytorch 2.7.1+cpu
+- Datasets 4.2.0
+- Tokenizers 0.22.1

config.json

@@ -1,40 +1,40 @@
-{
-  "architectures": [
-    "BertForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "dtype": "float32",
-  "embedding_size": 768,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Education, Health & Social Welfare",
-    "1": "Infrastructure, Utilities & Natural Resources",
-    "2": "Municipal Governance & Community Services",
-    "3": "Other / Unknown",
-    "4": "Security & Law Enforcement"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Education, Health & Social Welfare": 0,
-    "Infrastructure, Utilities & Natural Resources": 1,
-    "Municipal Governance & Community Services": 2,
-    "Other / Unknown": 3,
-    "Security & Law Enforcement": 4
-  },
-  "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",
-  "transformers_version": "4.57.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 197285
-}
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Education, Health & Social Welfare",
+    "1": "Infrastructure, Utilities & Natural Resources",
+    "2": "Municipal Governance & Community Services",
+    "3": "Other / Unknown",
+    "4": "Security & Law Enforcement"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Education, Health & Social Welfare": 0,
+    "Infrastructure, Utilities & Natural Resources": 1,
+    "Municipal Governance & Community Services": 2,
+    "Other / Unknown": 3,
+    "Security & Law Enforcement": 4
+  },
+  "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",
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 197285
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b19d68f4988359325b410ff4610b3fc89b4b86546b95a9f37e45cd016a5cfbc
+oid sha256:f5d147df69aa2dbf059cb1968f32ea024648c56234794c5a8ac83efe13fefde5
 size 950263820

special_tokens_map.json

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

tokenizer_config.json

@@ -1,59 +1,59 @@
-{
-  "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
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "104": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "105": {
-      "content": "[SEP]",
-      "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": false,
-  "extra_special_tokens": {},
-  "lowercase": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": false,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}
+{
+  "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
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "[SEP]",
+      "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": false,
+  "extra_special_tokens": {},
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437d1beb508900fdd412db72978b5c8b37b325140c831735f62c1913cc3bcebc
-size 5777
+oid sha256:e436925272baf4f1800ed3aacda85da3a81d776d32cb4b1a39c0e19cd3ee1e75
+size 5713