MuRIL for TamilQC

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7144
+- Precision: 0.9059
+- Recall: 0.9049
+- Accuracy: 0.9049
+- F1-score: 0.9053
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| 0.6607        | 1.0   | 309  | 0.3826          | 0.8915    | 0.8907 | 0.8907   | 0.8905   |
+| 0.2673        | 2.0   | 618  | 0.4694          | 0.8886    | 0.8866 | 0.8866   | 0.8860   |
+| 0.1819        | 3.0   | 927  | 0.4766          | 0.9001    | 0.8988 | 0.8988   | 0.8989   |
+| 0.102         | 4.0   | 1236 | 0.6096          | 0.8945    | 0.8927 | 0.8927   | 0.8930   |
+| 0.0607        | 5.0   | 1545 | 0.6537          | 0.8971    | 0.8947 | 0.8947   | 0.8955   |
+| 0.0326        | 6.0   | 1854 | 0.6568          | 0.9127    | 0.9109 | 0.9109   | 0.9116   |
+| 0.0221        | 7.0   | 2163 | 0.7081          | 0.9045    | 0.9028 | 0.9028   | 0.9035   |
+| 0.0133        | 8.0   | 2472 | 0.7144          | 0.9059    | 0.9049 | 0.9049   | 0.9053   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "google/muril-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Abbreviation",
+    "1": "Description",
+    "2": "Entity",
+    "3": "Human",
+    "4": "Location",
+    "5": "Numeric"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Abbreviation": 0,
+    "Description": 1,
+    "Entity": 2,
+    "Human": 3,
+    "Location": 4,
+    "Numeric": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 197285
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc64af6f109935cc9432bb9b419416bdff7fe1f4140f2e1c74c90915f17ffe7
+size 2023700848

runs/Mar26_08-35-26_a188f270a8c2/events.out.tfevents.1711442363.a188f270a8c2.176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8724cc6b88964f043c57432e44a79476e33e4911360d1980d976f453e66a9ef1
+size 10669

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 +1,58 @@
+{
+  "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,
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80da42a4639d0fa5d3d50362fd788f0a9d4f3d24530f49c46737ec07dcddb243
+size 4856