xlm-roberta-base_ary_corr_2e-05 – AI Model by Shijia | AlphaNeural AI

You can deploy this model and start earning money today!

Shijia/
xlm-roberta-base_ary_corr_2e-05

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

xlm-roberta-base_ary_corr_2e-05

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: 0.0224
Spearman Corr: 0.7768

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
No log	0.9	200	0.0245	0.7744
No log	1.8	400	0.0227	0.7757
0.0016	2.7	600	0.0226	0.7790
0.0016	3.6	800	0.0240	0.7742
0.0015	4.5	1000	0.0226	0.7764
0.0015	5.41	1200	0.0228	0.7778
0.0014	6.31	1400	0.0220	0.7796
0.0014	7.21	1600	0.0232	0.7737
0.0013	8.11	1800	0.0222	0.7790
0.0013	9.01	2000	0.0217	0.7800
0.0013	9.91	2200	0.0228	0.7798
0.0011	10.81	2400	0.0223	0.7781
0.0011	11.71	2600	0.0232	0.7782
0.0011	12.61	2800	0.0217	0.7798
0.0011	13.51	3000	0.0240	0.7747
0.001	14.41	3200	0.0226	0.7771
0.001	15.32	3400	0.0227	0.7773
0.0009	16.22	3600	0.0224	0.7768

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2