xlm-roberta-base_lr0.0001_seed42_kin-hau-eng_train – AI Model by shanhy | AlphaNeural AI

You can deploy this model and start earning money today!

shanhy/
xlm-roberta-base_lr0.0001_seed42_kin-hau-eng_train

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

xlm-roberta-base_lr0.0001_seed42_kin-hau-eng_train

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: 0.0498
Spearman Corr: -0.0264

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: 0.0001
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
No log	0.53	200	0.0507	-0.0530
No log	1.06	400	0.0492	0.0480
No log	1.6	600	0.0543	nan
0.0606	2.13	800	0.0543	nan
0.0606	2.66	1000	0.0490	nan
0.0606	3.19	1200	0.0526	nan
0.0606	3.72	1400	0.0544	0.0219
0.0572	4.26	1600	0.0572	-0.0115
0.0572	4.79	1800	0.0541	-0.0400
0.0572	5.32	2000	0.0617	nan
0.0572	5.85	2200	0.0491	0.0023
0.0562	6.38	2400	0.0493	-0.0814
0.0562	6.91	2600	0.0561	0.0451
0.0562	7.45	2800	0.0563	nan
0.0562	7.98	3000	0.0498	-0.0264

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2