Downloads · 30 days
13
43% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.1_s13_pre_ep5
xlmr-sold_mrp0.1_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
13
43% 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/sold_mrp_to_hs_v2/runs/6ra7erkv
Epochs: 5
Steps: 409
Validation Time: 0.01s
Validation Loss: 0.105838
Validation Accuracy: 0.944895
Validation F1: 0.628468
{'0': {'precision': 0.9518040558335528, 'recall': 0.99169925224669, 'f1-score': 0.971342180413237, 'support': 29154.0}, '1': {'precision': 0.5849056603773585, 'recall': 0.1889196675900277, 'f1-score': 0.28559463986599665, 'support': 1805.0}, 'accuracy': 0.944894860945121, 'macro avg': {'precision': 0.7683548581054556, 'recall': 0.5903094599183588, 'f1-score': 0.6284684101396169, 'support': 30959.0}, 'weighted avg': {'precision': 0.930412809223571, 'recall': 0.944894860945121, 'f1-score': 0.931361098637735, 'support': 30959.0}}
Masked Accuracy: 0.958589
Masked F1: 0.767828
{'0': {'precision': 0.9616449189402926, 'recall': 0.9954973393368809, 'f1-score': 0.9782783588093322, 'support': 2443.0}, '1': {'precision': 0.8607594936708861, 'recall': 0.4121212121212121, 'f1-score': 0.5573770491803278, 'support': 165.0}, 'accuracy': 0.9585889570552147, 'macro avg': {'precision': 0.9112022063055893, 'recall': 0.7038092757290465, 'f1-score': 0.76782770399483, 'support': 2608.0}, 'weighted avg': {'precision': 0.9552622137372817, 'recall': 0.9585889570552147, 'f1-score': 0.951649249879583, '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