Step 18149

README.md

@@ -1,50 +1,106 @@
+
 ---
-tags: autonlp
 language: bn
-widget:
-- text: "I love AutoNLP 🤗"
-datasets:
-- albertvillanova/autonlp-data-baselines-indic_glue-multi_class_classification
+tags:
+- collaborative
+- bengali
+- SequenceClassification
+license: apache-2.0
+datasets: IndicGlue 
+metrics:
+- Loss
+- Accuracy
+- Precision
+- Recall
 ---
 
-# Model Trained Using AutoNLP
+# sahajBERT News Article Classification
 
-- Problem type: Multi-class Classification
-- Model ID: 1351187
+## Model description
 
-## Validation Metrics
+[sahajBERT](https://huggingface.co/neuropark/sahajBERT) fine-tuned for news article classification using the `sna.bn` split of [IndicGlue](https://huggingface.co/datasets/indic_glue). 
 
-- Loss: 0.46760785579681396
-- Accuracy: 0.8412473423104181
-- Macro F1: 0.8151341402067301
-- Micro F1: 0.8412473423104181
-- Weighted F1: 0.8458231431392536
-- Macro Precision: 0.804355047657178
-- Micro Precision: 0.8412473423104181
-- Weighted Precision: 0.8606653801556983
-- Macro Recall: 0.8328042776824057
-- Micro Recall: 0.8412473423104181
-- Weighted Recall: 0.8412473423104181
+The model is trained for classifying articles into 5 different classes:
 
+| Label id | Label |
+|:--------:|:----:|
+|0 | kolkata|
+|1 | state|
+|2 | national|
+|3 | sports|
+|4 | entertainment|
+|5 | international|
 
-## Usage
+## Intended uses & limitations
 
-You can use cURL to access this model:
+#### How to use
 
-```
-$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoNLP"}' https://api-inference.huggingface.co/models/albertvillanova/autonlp-baselines-indic_glue-multi_class_classification-1351187
-```
+You can use this model directly with a pipeline for Sequence Classification:
+```python
+from transformers import AlbertForSequenceClassification, TextClassificationPipeline, PreTrainedTokenizerFast
 
-Or Python API:
+# Initialize tokenizer
+tokenizer = PreTrainedTokenizerFast.from_pretrained("neuropark/sahajBERT-NCC")
 
+# Initialize model
+model = AlbertForSequenceClassification.from_pretrained("neuropark/sahajBERT-NCC")
+
+# Initialize pipeline
+pipeline = TextClassificationPipeline(tokenizer=tokenizer, model=model)
+
+raw_text = "এই ইউনিয়নে ৩ টি মৌজা ও ১০ টি গ্রাম আছে ।" # Change me
+output = pipeline(raw_text)
 ```
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-model = AutoModelForSequenceClassification.from_pretrained("albertvillanova/autonlp-baselines-indic_glue-multi_class_classification-1351187", use_auth_token=True)
+#### Limitations and bias
+
+<!-- Provide examples of latent issues and potential remediations. -->
+WIP
+
+## Training data
+
+The model was initialized with pre-trained weights of [sahajBERT](https://huggingface.co/neuropark/sahajBERT) at step 18149 and trained on the `sna.bn` split of [IndicGlue](https://huggingface.co/datasets/indic_glue). 
+
+## Training procedure
+
+Coming soon! 
+<!-- ```bibtex
+@inproceedings{...,
+  year={2020}
+}
+``` -->
+
+## Eval results
+
+accuracy: 0.920623671155209
+
+loss: 0.2719293534755707
+
+macro_f1: 0.8924089161713425
+
+macro_precision: 0.891858452957785
+
+macro_recall: 0.8978917764271065
+
+micro_f1: 0.920623671155209
+
+micro_precision: 0.920623671155209
+
+micro_recall: 0.920623671155209
+
+weighted_f1: 0.9205158122362266
+
+weighted_precision: 0.9236142214371135
+
+weighted_recall: 0.920623671155209
+
 
-tokenizer = AutoTokenizer.from_pretrained("albertvillanova/autonlp-baselines-indic_glue-multi_class_classification-1351187", use_auth_token=True)
 
-inputs = tokenizer("I love AutoNLP", return_tensors="pt")
+### BibTeX entry and citation info
 
-outputs = model(**inputs)
-```
+Coming soon! 
+<!-- ```bibtex
+@inproceedings{...,
+  year={2020}
+}
+``` -->

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "AutoNLP",
+  "_name_or_path": "albertvillanova/autonlp-indic_glue-multi_class_classification-218510d-1261095",
   "_num_labels": 6,
   "architectures": [
     "AlbertForSequenceClassification"
@@ -34,7 +34,7 @@
     "5": 5
   },
   "layer_norm_eps": 1e-12,
-  "max_length": 64,
+  "max_length": 128,
   "max_position_embeddings": 512,
   "model_type": "albert",
   "net_structure_type": 0,
@@ -45,7 +45,7 @@
   "pad_token_id": 0,
   "padding": "max_length",
   "position_embedding_type": "absolute",
-  "transformers_version": "4.5.1",
+  "transformers_version": "4.6.1",
   "type_vocab_size": 2,
   "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e8371df57f6d4a19d894cf5806b64b6cd1b9d987a79f2dec6633be1cd7c055
-size 71800683
+oid sha256:004246afd25a31f2276508f7fbfff866db2c4b3ce7dad33239ad8568d01c3f24
+size 71800235