Downloads · 30 days
14
45% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.1_s13_pre_ep4
xlmr-sold_mrp0.1_s13_pre_ep4 is a machine learning model from s-haturusinghe. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
14
45% of all-time downloads
All-time downloads
31
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 100%
From the Hugging Face model README
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Wandb Run URL: https://wandb.ai/s_haturusinghe-university-of-kelaniya/sold_mrp_to_hs_v2/runs/6ra7erkv
Epochs: 4
Steps: 0
Validation Time: 0.01s
Validation Loss: 0.088426
Validation Accuracy: 0.944604
Validation F1: 0.631103
{'0': {'precision': 0.9521173175152414, 'recall': 0.9910132400356726, 'f1-score': 0.9711759861510277, 'support': 29154.0}, '1': {'precision': 0.5732899022801303, 'recall': 0.19501385041551247, 'f1-score': 0.2910293509714758, 'support': 1805.0}, 'accuracy': 0.9446041538809393, 'macro avg': {'precision': 0.7627036098976858, 'recall': 0.5930135452255926, 'f1-score': 0.6311026685612517, 'support': 30959.0}, 'weighted avg': {'precision': 0.9300305742580504, 'recall': 0.9446041538809393, 'f1-score': 0.9315214534949636, 'support': 30959.0}}
Masked Accuracy: 0.963190
Masked F1: 0.846455
{'0': {'precision': 0.9779321618308132, 'recall': 0.9827515400410678, 'f1-score': 0.9803359278984023, 'support': 2435.0}, '1': {'precision': 0.7391304347826086, 'recall': 0.6878612716763006, 'f1-score': 0.7125748502994012, 'support': 173.0}, 'accuracy': 0.9631901840490797, 'macro avg': {'precision': 0.8585312983067109, 'recall': 0.8353064058586842, 'f1-score': 0.8464553890989017, 'support': 2608.0}, 'weighted avg': {'precision': 0.962091403096404, 'recall': 0.9631901840490797, 'f1-score': 0.9625741693000023, 'support': 2608.0}}
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.1
"seed": 13
"dataset": sold
"finetuning_stage": pre
"val_int": 10000
"patience": 3
"skip_empty_rat": True