update model card README.md

README.md

@@ -1,40 +1,66 @@
 ---
-language: mr
+license: apache-2.0
+tags:
+- generated_from_trainer
 datasets:
 - wikiann
-examples:
-widget:
-- text: "राज्यसभा निवडणुकांसाठी उद्या मुंबईत मतदान होणार आहे."
-  example_title: "Sentence_1"
-- text: "विराट कोहली भारताकडून खेळतो."
-  example_title: "Sentence_2"
-- text: "नवी दिल्ली ही भारताची राजधानी आहे"
-  example_title: "Sentence_3"
+model-index:
+- name: ner_marathi_bert
+  results: []
 ---
 
-<h1>Marathi Named Entity Recognition Model trained using transfer learning</h1>
-Fine-tuning bert-base-multilingual-cased on Wikiann dataset for performing NER on Marathi language.
+<!-- 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. -->
 
+# ner_marathi_bert
 
-## Label ID and its corresponding label name
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the wikiann dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3606
+- Overall Precision: 0.8939
+- Overall Recall: 0.9030
+- Overall F1: 0.8984
+- Overall Accuracy: 0.9347
+- Loc F1: 0.8823
+- Org F1: 0.8555
+- Per F1: 0.9435
 
-Label list: (0), B-PER (1), I-PER (2), B-ORG (3), I-ORG (4), B-LOC (5), I-LOC (6)
+## Model description
 
+More information needed
 
-Example
-```py
-from transformers import AutoTokenizer, AutoModelForTokenClassification
-from transformers import pipeline
+## Intended uses & limitations
 
-tokenizer = AutoTokenizer.from_pretrained("lakshaywadhwa1993/ner_marathi_bert")
+More information needed
 
-model = AutoModelForTokenClassification.from_pretrained("lakshaywadhwa1993/ner_marathi_bert")
+## Training and evaluation data
 
-nlp = pipeline("ner", model=model, tokenizer=tokenizer)
+More information needed
 
-example = ["राज्यसभा","निवडणुकांसाठी","मुंबईत","भाजपचे" ,"चिंचवडचे", "आमदार", "लक्ष्मण", "जगताप"]
+## Training procedure
 
-results = nlp(example)
+### Training hyperparameters
 
-results
-```
+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: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Loc F1 | Org F1 | Per F1 |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:------:|:------:|:------:|
+| 0.2961        | 3.19  | 1000 | 0.3496          | 0.8720            | 0.8841         | 0.8780     | 0.9229           | 0.8599 | 0.8210 | 0.9343 |
+| 0.0613        | 6.39  | 2000 | 0.3606          | 0.8939            | 0.9030         | 0.8984     | 0.9347           | 0.8823 | 0.8555 | 0.9435 |
+
+
+### Framework versions
+
+- Transformers 4.21.0
+- Pytorch 1.12.0+cu113
+- Datasets 2.4.0
+- Tokenizers 0.12.1