MuRIL_for_TamilQC

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: google/muril-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: Muril-base-finetune-Tamil-questions
+  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. -->
+
+# Muril-base-finetune-Tamil-questions
+
+This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4081
+- Precision: 0.9205
+- Recall: 0.9198
+- Accuracy: 0.9198
+- F1-score: 0.9199
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| 1.5732        | 1.0   | 305  | 1.2601          | 0.8743    | 0.8858 | 0.8858   | 0.8790   |
+| 0.9937        | 2.0   | 610  | 0.7465          | 0.8988    | 0.9098 | 0.9098   | 0.9033   |
+| 0.5354        | 3.0   | 915  | 0.4557          | 0.9044    | 0.9158 | 0.9158   | 0.9092   |
+| 0.2862        | 4.0   | 1220 | 0.3772          | 0.9198    | 0.9198 | 0.9198   | 0.9193   |
+| 0.1724        | 5.0   | 1525 | 0.3306          | 0.9274    | 0.9259 | 0.9259   | 0.9261   |
+| 0.1235        | 6.0   | 1830 | 0.3763          | 0.9214    | 0.9158 | 0.9158   | 0.9171   |
+| 0.0902        | 7.0   | 2135 | 0.3808          | 0.9229    | 0.9218 | 0.9218   | 0.9219   |
+| 0.0644        | 8.0   | 2440 | 0.3974          | 0.9229    | 0.9218 | 0.9218   | 0.9220   |
+| 0.0575        | 9.0   | 2745 | 0.3930          | 0.9224    | 0.9218 | 0.9218   | 0.9218   |
+| 0.0483        | 10.0  | 3050 | 0.4081          | 0.9205    | 0.9198 | 0.9198   | 0.9199   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "google/muril-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Abbreviation",
+    "1": "Description",
+    "2": "Entity",
+    "3": "Human",
+    "4": "Location",
+    "5": "Numeric"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "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:e5a2689de4e02ad023a357e79568a9f7cdce74224b41f9b89bc26136cc23ce78
+size 950266896

runs/May14_06-21-12_da90288f2825/events.out.tfevents.1715667704.da90288f2825.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794c4b642431f8d3076fe7b99d71ffd944be48bd33ab3f7d8a916ea40fbd50e6
+size 4933

runs/May14_06-26-43_da90288f2825/events.out.tfevents.1715668012.da90288f2825.157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2ca9ec802e195ba51075c2d3a48510f80fdb2ea47338701e848c7d5e09fe0c
+size 12180

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:d691c3515e10bb49fdb13d9706d383ce667e8f94f627c69688af5b5f134443b7
+size 4984