xlm-roberta-base_hin_corr_2e-05 – AI Model by Shijia | AlphaNeural AI

You can deploy this model and start earning money today!

Shijia/
xlm-roberta-base_hin_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_hin_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: 0.0209
Spearman Corr: 0.7808

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	0.85	200	0.0208	0.7783
No log	1.69	400	0.0214	0.7813
0.0006	2.54	600	0.0214	0.7775
0.0006	3.38	800	0.0211	0.7811
0.0006	4.23	1000	0.0208	0.7799
0.0006	5.07	1200	0.0213	0.7807
0.0006	5.92	1400	0.0218	0.7775
0.0006	6.77	1600	0.0206	0.7817
0.0006	7.61	1800	0.0213	0.7821
0.0005	8.46	2000	0.0213	0.7804
0.0005	9.3	2200	0.0218	0.7812
0.0004	10.15	2400	0.0215	0.7793
0.0004	10.99	2600	0.0215	0.7794
0.0004	11.84	2800	0.0212	0.7815
0.0004	12.68	3000	0.0221	0.7763
0.0004	13.53	3200	0.0215	0.7782
0.0004	14.38	3400	0.0209	0.7808

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2