Downloads · 30 days
13
45% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.75_s13_pre_ep3
xlmr-sold_mrp0.75_s13_pre_ep3 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
13
45% of all-time downloads
All-time downloads
29
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/niszfrce
Epochs: 3
Steps: 0
Validation Time: 0.01s
Validation Loss: 0.058109
Validation Accuracy: 0.943829
Validation F1: 0.618984
{'0': {'precision': 0.9510381362903492, 'recall': 0.9913905467517322, 'f1-score': 0.9707951969099001, 'support': 29154.0}, '1': {'precision': 0.5580985915492958, 'recall': 0.17562326869806094, 'f1-score': 0.2671723556679309, 'support': 1805.0}, 'accuracy': 0.9438289350431216, 'macro avg': {'precision': 0.7545683639198224, 'recall': 0.5835069077248966, 'f1-score': 0.6189837762889155, 'support': 30959.0}, 'weighted avg': {'precision': 0.9281286147212545, 'recall': 0.9438289350431216, 'f1-score': 0.9297719329659176, 'support': 30959.0}}
Masked Accuracy: 0.979498
Masked F1: 0.906092
{'0': {'precision': 0.9850984566258648, 'recall': 0.9931710648261061, 'f1-score': 0.9891182900170027, 'support': 20501.0}, '1': {'precision': 0.8815566835871405, 'recall': 0.7718518518518519, 'f1-score': 0.8230647709320695, 'support': 1350.0}, 'accuracy': 0.9794975058349732, 'macro avg': {'precision': 0.9333275701065027, 'recall': 0.882511458338979, 'f1-score': 0.906091530474536, 'support': 21851.0}, 'weighted avg': {'precision': 0.9787014316108871, 'recall': 0.9794975058349732, 'f1-score': 0.9788591599650756, 'support': 21851.0}}
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.75
"seed": 13
"dataset": sold
"finetuning_stage": pre
"val_int": 10000
"patience": 3
"skip_empty_rat": True