MuRIL_for_TamilQC

README.md

@@ -0,0 +1,73 @@
+---
+base_model: google/muril-large-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: Muril-base-finetune-Tamil-qc
+  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-qc
+
+This model is a fine-tuned version of [google/muril-large-cased](https://huggingface.co/google/muril-large-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8454
+- Precision: 0.8906
+- Recall: 0.8887
+- Accuracy: 0.8887
+- F1-score: 0.8891
+
+## 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: 5e-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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| 0.8303        | 1.0   | 309  | 1.7865          | 0.0487    | 0.2206 | 0.2206   | 0.0798   |
+| 0.4838        | 2.0   | 618  | 0.4928          | 0.8792    | 0.8725 | 0.8725   | 0.8729   |
+| 0.2588        | 3.0   | 927  | 0.5815          | 0.8742    | 0.8725 | 0.8725   | 0.8722   |
+| 0.2287        | 4.0   | 1236 | 0.5803          | 0.8767    | 0.8765 | 0.8765   | 0.8760   |
+| 0.1217        | 5.0   | 1545 | 0.7215          | 0.8773    | 0.8725 | 0.8725   | 0.8739   |
+| 0.0752        | 6.0   | 1854 | 0.6988          | 0.8938    | 0.8907 | 0.8907   | 0.8914   |
+| 0.0416        | 7.0   | 2163 | 0.7899          | 0.8966    | 0.8927 | 0.8927   | 0.8937   |
+| 0.0247        | 8.0   | 2472 | 0.8132          | 0.8927    | 0.8907 | 0.8907   | 0.8912   |
+| 0.0242        | 9.0   | 2781 | 0.8443          | 0.8944    | 0.8927 | 0.8927   | 0.8930   |
+| 0.0129        | 10.0  | 3090 | 0.8454          | 0.8906    | 0.8887 | 0.8887   | 0.8891   |
+
+
+### 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-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": "4.39.3",
+  "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 sha256:10b4f5a70c4508f5517a17b5ebec3d4aa90c3a3128c8d58ca3fd45982e7382db
+size 2023700848

runs/Apr23_09-07-39_2a5b8b93632b/events.out.tfevents.1713863281.2a5b8b93632b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6512d3865f4ad7094985196dd36a867417defc6f3708040e8f4b4a97fb68e5
+size 15606

runs/Apr23_09-17-58_2a5b8b93632b/events.out.tfevents.1713863887.2a5b8b93632b.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d9cc0d5847df6cdc8a77f833ee95b1acaac69fe4b8af7696415ef195e34d25
+size 10780

runs/Apr23_09-17-58_2a5b8b93632b/events.out.tfevents.1713864252.2a5b8b93632b.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c164f16fdf6daa2d680730067b74dbedbdb1f6e7b607eb47c5d1497501563f96
+size 10780

runs/Apr23_09-32-31_2a5b8b93632b/events.out.tfevents.1713864761.2a5b8b93632b.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb827e70860adc50bc075ac428a2557e342f87660da3b0beceb5dd9595249c1d
+size 12159

runs/Apr23_09-41-51_2a5b8b93632b/events.out.tfevents.1713865325.2a5b8b93632b.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33218343808a44a394fb1e00c896365ff18662fec88cabd6ac421d2e263ccb5f
+size 12159

runs/Apr23_09-56-24_2a5b8b93632b/events.out.tfevents.1713866227.2a5b8b93632b.34.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270b3cef421638185960e0a3085361f603fcb0d1bb5a2cbbc74166aa38580d67
+size 12156

runs/Apr23_10-44-26_2a5b8b93632b/events.out.tfevents.1713869082.2a5b8b93632b.34.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77e344fd82a8335657b56d700f7893899eba924fc2e39bd7fa83e51ff5ec661
+size 12156

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:b0854a1dd956f36148e18672401cbc9ff46ab3dc1c5d07a8ff2006bc231e9af5
+size 4920