xlm-roberta-base_eng_corr_5e-06 – AI Model by Shijia | AlphaNeural AI

You can deploy this model and start earning money today!

Shijia/
xlm-roberta-base_eng_corr_5e-06

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

xlm-roberta-base_eng_corr_5e-06

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: 0.0255
Spearman Corr: 0.7564

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: 5e-06
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	1.33	200	0.0260	0.7496
0.0044	2.66	400	0.0249	0.7543
0.0041	3.99	600	0.0253	0.7530
0.0041	5.32	800	0.0267	0.7556
0.0038	6.64	1000	0.0256	0.7552
0.0036	7.97	1200	0.0262	0.7513
0.0036	9.3	1400	0.0262	0.7556
0.0035	10.63	1600	0.0251	0.7516
0.0034	11.96	1800	0.0249	0.7522
0.0034	13.29	2000	0.0246	0.7544
0.0032	14.62	2200	0.0254	0.7517
0.0031	15.95	2400	0.0259	0.7561
0.0031	17.28	2600	0.0262	0.7555
0.003	18.6	2800	0.0260	0.7570
0.0029	19.93	3000	0.0253	0.7549
0.0029	21.26	3200	0.0245	0.7568
0.0029	22.59	3400	0.0254	0.7557
0.0029	23.92	3600	0.0254	0.7556
0.0029	25.25	3800	0.0248	0.7573
0.0028	26.58	4000	0.0254	0.7568
0.0027	27.91	4200	0.0254	0.7571
0.0027	29.24	4400	0.0255	0.7564

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2