Downloads · 30 days
14
48% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.25_s13_pre_ep5
xlmr-sold_mrp0.25_s13_pre_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
14
48% 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/q8y9k7xt
Epochs: 5
Steps: 409
Validation Time: 0.01s
Validation Loss: 0.030280
Validation Accuracy: 0.944927
Validation F1: 0.632086
{'0': {'precision': 0.9521628834052647, 'recall': 0.9913219455306305, 'f1-score': 0.9713479086494026, 'support': 29154.0}, '1': {'precision': 0.5825082508250825, 'recall': 0.1955678670360111, 'f1-score': 0.29282455412691827, 'support': 1805.0}, 'accuracy': 0.94492716173003, 'macro avg': {'precision': 0.7673355671151736, 'recall': 0.5934449062833208, 'f1-score': 0.6320862313881604, 'support': 30959.0}, 'weighted avg': {'precision': 0.9306109401316697, 'recall': 0.94492716173003, 'f1-score': 0.9317880179903669, 'support': 30959.0}}
Masked Accuracy: 0.991839
Masked F1: 0.963060
{'0': {'precision': 0.9919583023082651, 'recall': 0.9993998499624906, 'f1-score': 0.9956651718983558, 'support': 6665.0}, '1': {'precision': 0.9897959183673469, 'recall': 0.8778280542986425, 'f1-score': 0.9304556354916067, 'support': 442.0}, 'accuracy': 0.9918390319403405, 'macro avg': {'precision': 0.990877110337806, 'recall': 0.9386139521305665, 'f1-score': 0.9630604036949812, 'support': 7107.0}, 'weighted avg': {'precision': 0.9918238188832073, 'recall': 0.9918390319403405, 'f1-score': 0.9916096470507711, 'support': 7107.0}}
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.25
"seed": 13
"dataset": sold
"finetuning_stage": pre
"val_int": 10000
"patience": 3
"skip_empty_rat": True