DGurgurov commited on
Commit
80b29e7
1 Parent(s): 4a1aff2

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +36 -0
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # Fine-tuned XLM-R Model for latvian Sentiment Analysis
3
+
4
+ This is a fine-tuned XLM-R model for sentiment analysis in latvian.
5
+
6
+ ## Model Details
7
+
8
+ - **Model Name**: XLM-R Sentiment Analysis
9
+ - **Language**: latvian
10
+ - **Fine-tuning Dataset**: DGurgurov/latvian_sa
11
+
12
+ ## Training Details
13
+
14
+ - **Epochs**: 20
15
+ - **Batch Size**: 32 (train), 64 (eval)
16
+ - **Optimizer**: AdamW
17
+ - **Learning Rate**: 5e-5
18
+
19
+ ## Performance Metrics
20
+
21
+ - **Accuracy**: 0.77600
22
+ - **Macro F1**: 0.76850
23
+ - **Micro F1**: 0.77600
24
+
25
+ ## Usage
26
+
27
+ To use this model, you can load it with the Hugging Face Transformers library:
28
+ ```python
29
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
30
+
31
+ tokenizer = AutoTokenizer.from_pretrained("DGurgurov/xlm-r_latvian_sentiment")
32
+ model = AutoModelForSequenceClassification.from_pretrained("DGurgurov/xlm-r_latvian_sentiment")
33
+ ```
34
+
35
+ ## License
36
+ [MIT]