MuRIL_for_TeluguQC

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: google/muril-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: Muril-base-finetune-Telugu-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-Telugu-qc
+
+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: 1.6250
+- Precision: 0.7716
+- Recall: 0.7647
+- Accuracy: 0.7647
+- F1-score: 0.7587
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| 1.7858        | 1.0   | 32   | 1.7821          | 0.0454    | 0.2130 | 0.2130   | 0.0748   |
+| 1.7526        | 2.0   | 64   | 1.7539          | 0.1754    | 0.2860 | 0.2860   | 0.1866   |
+| 1.7112        | 3.0   | 96   | 1.7232          | 0.3352    | 0.3043 | 0.3043   | 0.2168   |
+| 1.6655        | 4.0   | 128  | 1.6832          | 0.7122    | 0.6166 | 0.6166   | 0.6194   |
+| 1.6217        | 5.0   | 160  | 1.6496          | 0.7708    | 0.7688 | 0.7688   | 0.7629   |
+| 1.5898        | 6.0   | 192  | 1.6431          | 0.7618    | 0.7424 | 0.7424   | 0.7379   |
+| 1.5678        | 7.0   | 224  | 1.6285          | 0.7697    | 0.7627 | 0.7627   | 0.7565   |
+| 1.5572        | 8.0   | 256  | 1.6250          | 0.7716    | 0.7647 | 0.7647   | 0.7587   |
+
+
+### 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-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": "4.38.2",
+  "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 sha256:9b85ca71ae55461247b0c3c451f9fbcd3af094e027628ec1b6c8397e8880713a
+size 950266896

runs/Apr09_10-05-09_d477a7e83fd3/events.out.tfevents.1712657123.d477a7e83fd3.893.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af9cf98714e535f316374811a930d7283d9722bd18549b7aa499f13902e570d
+size 10710

runs/Apr09_10-14-22_d477a7e83fd3/events.out.tfevents.1712657673.d477a7e83fd3.893.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4deee53958f1c7fb749368644c213ad9d5a9d58f8a67d209160992efd6f958
+size 10710

runs/Apr09_10-24-43_d477a7e83fd3/events.out.tfevents.1712658295.d477a7e83fd3.893.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6913bb053e822d70c6db372575d98c5c10121d2570ea8cd02c51e153ee4cbd9b
+size 10647

runs/Apr09_10-33-53_d477a7e83fd3/events.out.tfevents.1712658845.d477a7e83fd3.893.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233f1dad0210d17da5518b7f5858df159cb8bd683c2b786d00f5cdbd03293d18
+size 9321

runs/Apr09_10-43-40_d477a7e83fd3/events.out.tfevents.1712659433.d477a7e83fd3.893.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6059380022d3a83abe3ebc756a0f21c9ce3ea92b3dc8d08b2d8323eace5d4736
+size 7943

runs/Apr09_10-49-12_d477a7e83fd3/events.out.tfevents.1712659765.d477a7e83fd3.893.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94eb4ce54c57a42cf4b0fbce1eb51971bbd90bdec524139be36919a7826c2755
+size 8632

runs/Apr09_10-57-56_d477a7e83fd3/events.out.tfevents.1712660288.d477a7e83fd3.893.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e328f7d356e4c303c80d6f71fa5b149ff90e8bf179c0908eaf2f92c80796be
+size 8632

runs/Apr09_11-05-35_d477a7e83fd3/events.out.tfevents.1712660746.d477a7e83fd3.893.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4414e61eaca1c7c5cefa25879d4d7226fdc9be4ef1bb453480669596e838963
+size 10699

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": 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce89c89c9fe9c4e84e565023fc0ceea131345b8fc44a6a1689cf58772eae2676
+size 4920