Downloads · 30 days
12
36% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.75_s13_pre_ep5
xlmr-sold_mrp0.75_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
12
36% of all-time downloads
All-time downloads
33
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: 5
Steps: 409
Validation Time: 0.01s
Validation Loss: 0.051908
Validation Accuracy: 0.943086
Validation F1: 0.618724
{'0': {'precision': 0.9511198945981555, 'recall': 0.9904644302668587, 'f1-score': 0.9703935208522364, 'support': 29154.0}, '1': {'precision': 0.5358931552587646, 'recall': 0.1778393351800554, 'f1-score': 0.2670549084858569, 'support': 1805.0}, 'accuracy': 0.9430860169902129, 'macro avg': {'precision': 0.74350652492846, 'recall': 0.5841518827234571, 'f1-score': 0.6187242146690466, 'support': 30959.0}, 'weighted avg': {'precision': 0.9269109645775605, 'recall': 0.9430860169902129, 'f1-score': 0.9293868282807284, 'support': 30959.0}}
Masked Accuracy: 0.983845
Masked F1: 0.928465
{'0': {'precision': 0.989214924212981, 'recall': 0.9936075733177182, 'f1-score': 0.991406383134114, 'support': 20493.0}, '1': {'precision': 0.8966061562746646, 'recall': 0.8365243004418262, 'f1-score': 0.8655238095238095, 'support': 1358.0}, 'accuracy': 0.9838451329458606, 'macro avg': {'precision': 0.9429105402438227, 'recall': 0.9150659368797722, 'f1-score': 0.9284650963289618, 'support': 21851.0}, 'weighted avg': {'precision': 0.9834594573299902, 'recall': 0.9838451329458606, 'f1-score': 0.9835830096060011, '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