Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ language:
|
|
5 |
pipeline_tag: text-classification
|
6 |
---
|
7 |
# Sentiment Analysis Model for Azerbaijani Text
|
8 |
-
This repository hosts a fine-tuned XLM-RoBERTa model for sentiment analysis on Azerbaijani text. The model is capable of classifying text into three categories: negative, neutral, and positive.
|
9 |
|
10 |
## Model Description
|
11 |
The model is based on `xlm-roberta-base`, which has been fine-tuned on a diverse dataset of Azerbaijani text samples. It is designed to understand the sentiment expressed in texts and classify them accordingly.
|
@@ -66,30 +66,6 @@ The model outputs a label for each prediction, corresponding to one of the langu
|
|
66 |
| 2 | positive |
|
67 |
|
68 |
|
69 |
-
This mapping is utilized to decode the model's predictions into understandable language names, facilitating the interpretation of results for further processing or analysis.
|
70 |
-
|
71 |
-
|
72 |
-
Training Performance
|
73 |
-
|
74 |
-
The model was trained over three epochs, showing consistent improvement in accuracy and loss:
|
75 |
-
|
76 |
-
Epoch 1: Training Loss: 0.0127, Validation Loss: 0.0174, Accuracy: 0.9966, F1 Score: 0.9966
|
77 |
-
Epoch 2: Training Loss: 0.0149, Validation Loss: 0.0141, Accuracy: 0.9973, F1 Score: 0.9973
|
78 |
-
Epoch 3: Training Loss: 0.0001, Validation Loss: 0.0109, Accuracy: 0.9984, F1 Score: 0.9984
|
79 |
-
|
80 |
-
Test Results
|
81 |
-
|
82 |
-
The model achieved the following results on the test set:
|
83 |
-
|
84 |
-
Loss: 0.0133
|
85 |
-
Accuracy: 0.9975
|
86 |
-
F1 Score: 0.9975
|
87 |
-
Precision: 0.9975
|
88 |
-
Recall: 0.9975
|
89 |
-
Evaluation Time: 17.5 seconds
|
90 |
-
Samples per Second: 599.685
|
91 |
-
Steps per Second: 9.424
|
92 |
-
|
93 |
|
94 |
License
|
95 |
|
|
|
5 |
pipeline_tag: text-classification
|
6 |
---
|
7 |
# Sentiment Analysis Model for Azerbaijani Text
|
8 |
+
This repository hosts a fine-tuned XLM-RoBERTa model for sentiment analysis on Azerbaijani text. The model is capable of classifying text into three categories: negative, neutral, and positive.
|
9 |
|
10 |
## Model Description
|
11 |
The model is based on `xlm-roberta-base`, which has been fine-tuned on a diverse dataset of Azerbaijani text samples. It is designed to understand the sentiment expressed in texts and classify them accordingly.
|
|
|
66 |
| 2 | positive |
|
67 |
|
68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
|
70 |
License
|
71 |
|