Downloads · 30 days
12
40% of all-time downloads
s-haturusinghe/mrp_0.5_seed42_b16_e5_radam_s42_msk0.5_2_ep5
mrp_0.5_seed42_b16_e5_radam_s42_msk0.5_2_ep5 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
12
40% of all-time downloads
All-time downloads
30
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/xlmr-base-42-b16-e5-radam-s42-mrp-msk0.5/runs/ufmyp51c
Epochs: 5
Steps: 410
Validation Time: 0.01s
Validation Loss: 0.043211
Validation Accuracy: 0.941812
Validation F1: 0.619348
{'0': {'precision': 0.9489072749447869, 'recall': 0.9914244386279102, 'f1-score': 0.9697000320010779, 'support': 29036.0}, '1': {'precision': 0.5706896551724138, 'recall': 0.17597022860180755, 'f1-score': 0.26899634295002034, 'support': 1881.0}, 'accuracy': 0.9418119481191577, 'macro avg': {'precision': 0.7597984650586003, 'recall': 0.5836973336148589, 'f1-score': 0.6193481874755491, 'support': 30917.0}, 'weighted avg': {'precision': 0.9258963960499447, 'recall': 0.9418119481191577, 'f1-score': 0.9270689992648797, 'support': 30917.0}}
Masked Accuracy: 0.985985
Masked F1: 0.938382
{'0': {'precision': 0.9915260428080941, 'recall': 0.9935583046629091, 'f1-score': 0.9925411334552102, 'support': 13661.0}, '1': {'precision': 0.8985005767012687, 'recall': 0.870391061452514, 'f1-score': 0.8842224744608399, 'support': 895.0}, 'accuracy': 0.9859851607584501, 'macro avg': {'precision': 0.9450133097546813, 'recall': 0.9319746830577116, 'f1-score': 0.9383818039580251, 'support': 14556.0}, 'weighted avg': {'precision': 0.985806216470803, 'recall': 0.9859851607584501, 'f1-score': 0.985880979580522, 'support': 14556.0}}
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.5
"seed": 42
"dataset": sold
"finetuning_stage": pre
"val_int": 10000
"patience": 3
"skip_empty_rat": True