Downloads · 30 days
13
45% of all-time downloads
s-haturusinghe/xlmr-sold_mrp0.75_s13_pre_ep2
xlmr-sold_mrp0.75_s13_pre_ep2 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
45% 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/niszfrce
Epochs: 2
Steps: 0
Validation Time: 0.01s
Validation Loss: 0.073933
Validation Accuracy: 0.943926
Validation F1: 0.626437
{'0': {'precision': 0.9517564094114546, 'recall': 0.990670233930164, 'f1-score': 0.9708235294117648, 'support': 29154.0}, '1': {'precision': 0.5562805872756933, 'recall': 0.1889196675900277, 'f1-score': 0.28205128205128205, 'support': 1805.0}, 'accuracy': 0.9439258373978487, 'macro avg': {'precision': 0.7540184983435739, 'recall': 0.5897949507600958, 'f1-score': 0.6264374057315234, 'support': 30959.0}, 'weighted avg': {'precision': 0.9286990154725339, 'recall': 0.9439258373978487, 'f1-score': 0.9306660984067041, 'support': 30959.0}}
Masked Accuracy: 0.974509
Masked F1: 0.885323
{'0': {'precision': 0.9847543212274228, 'recall': 0.9881607795371499, 'f1-score': 0.986454609566888, 'support': 20525.0}, '1': {'precision': 0.8063745019920319, 'recall': 0.7631975867269984, 'f1-score': 0.7841921735761332, 'support': 1326.0}, 'accuracy': 0.9745091757814288, 'macro avg': {'precision': 0.8955644116097273, 'recall': 0.8756791831320742, 'f1-score': 0.8853233915715106, 'support': 21851.0}, 'weighted avg': {'precision': 0.9739295699434481, 'recall': 0.9745091757814288, 'f1-score': 0.9741805722173965, '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