fine-tuned-DatasetQAS-Squad-ID-with-xlm-roberta-large-without-ITTL-without-freeze-LR-1e-05

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

• Loss: 1.3876
• Exact Match: 53.6102
• F1: 69.6077

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1
1.5313	0.5	463	1.4235	48.7014	66.1658
1.3868	1.0	926	1.3193	51.7189	68.5896
1.2618	1.5	1389	1.2877	52.8032	69.3561
1.1847	2.0	1852	1.2893	53.0218	69.7724
1.0884	2.5	2315	1.2777	53.3328	69.8210
1.0927	3.0	2778	1.2596	53.4000	69.9664
0.9519	3.5	3241	1.3342	53.6102	69.6168
0.9591	4.0	3704	1.3078	54.0640	69.9492
0.8586	4.49	4167	1.3876	53.6102	69.6077

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.2.0
• Tokenizers 0.13.2