xlm-roberta-base_eng_train_spearman_corr – AI Model by shanhy | AlphaNeural AI

You can deploy this model and start earning money today!

shanhy/
xlm-roberta-base_eng_train_spearman_corr

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

xlm-roberta-base_eng_train_spearman_corr

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0302
Spearman Corr: 0.8101

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Spearman Corr
0.0419	2.33	200	0.0169	0.7934
0.0205	4.65	400	0.0348	0.7991
0.0153	6.98	600	0.0285	0.8102
0.012	9.3	800	0.0280	0.8047
0.01	11.63	1000	0.0260	0.8106
0.0069	13.95	1200	0.0295	0.8054
0.0063	16.28	1400	0.0327	0.8099
0.0056	18.6	1600	0.0269	0.8028
0.005	20.93	1800	0.0319	0.8075
0.0046	23.26	2000	0.0292	0.8109
0.0043	25.58	2200	0.0305	0.8085
0.0039	27.91	2400	0.0302	0.8101

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2