xnli_xlm_r_only_hi

This model is a fine-tuned version of xlm-roberta-base on the xnli dataset. It achieves the following results on the evaluation set:

• Loss: 0.9182
• Accuracy: 0.7177

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: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7868	1.0	3068	0.7146	0.6968
0.673	2.0	6136	0.6719	0.7257
0.6153	3.0	9204	0.7021	0.7205
0.5663	4.0	12272	0.6964	0.7193
0.5212	5.0	15340	0.7119	0.7273
0.4789	6.0	18408	0.7596	0.7297
0.44	7.0	21476	0.8089	0.7129
0.4067	8.0	24544	0.8117	0.7185
0.3791	9.0	27612	0.9003	0.7189
0.3581	10.0	30680	0.9182	0.7177

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0
• Datasets 2.6.1
• Tokenizers 0.13.1