Downloads · 30 days
14
45% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.25_s13_pre_ep1
xlmr-sold_mrp0.25_s13_pre_ep1 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/q8y9k7xt
Epochs: 1
Steps: 0
Validation Time: 0.01s
Validation Loss: 0.141109
Validation Accuracy: 0.945509
Validation F1: 0.575447
{'0': {'precision': 0.9472141717411834, 'recall': 0.9977361597036427, 'f1-score': 0.971818986686267, 'support': 29154.0}, '1': {'precision': 0.736, 'recall': 0.10193905817174516, 'f1-score': 0.17907542579075425, 'support': 1805.0}, 'accuracy': 0.9455085758583933, 'macro avg': {'precision': 0.8416070858705917, 'recall': 0.549837608937694, 'f1-score': 0.5754472062385106, 'support': 30959.0}, 'weighted avg': {'precision': 0.9348997694674395, 'recall': 0.9455085758583933, 'f1-score': 0.9255997248426544, 'support': 30959.0}}
Masked Accuracy: 0.946532
Masked F1: 0.616482
{'0': {'precision': 0.9476380193511668, 'recall': 0.9982014388489209, 'f1-score': 0.9722627737226277, 'support': 6672.0}, '1': {'precision': 0.8481012658227848, 'recall': 0.15402298850574714, 'f1-score': 0.2607003891050584, 'support': 435.0}, 'accuracy': 0.9465315885746447, 'macro avg': {'precision': 0.8978696425869758, 'recall': 0.576112213677334, 'f1-score': 0.616481581413843, 'support': 7107.0}, 'weighted avg': {'precision': 0.9415456473538619, 'recall': 0.9465315885746447, 'f1-score': 0.9287099895227343, '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