distilroberta-base-ep20-phrase5k

This model is a fine-tuned version of judy93536/distilroberta-base-ep20 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1361
• Accuracy: 0.9540

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: 1.123335054745316e-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.28
• num_epochs: 13
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	1.0595	0.6046
1.0445	2.0	500	0.8412	0.6136
1.0445	3.0	750	0.6597	0.7197
0.6876	4.0	1000	0.5043	0.7768
0.6876	5.0	1250	0.3559	0.8709
0.3881	6.0	1500	0.2273	0.9289
0.3881	7.0	1750	0.1852	0.9369
0.1977	8.0	2000	0.1567	0.9449
0.1977	9.0	2250	0.1396	0.9510
0.1436	10.0	2500	0.1493	0.9489
0.1436	11.0	2750	0.1397	0.9499
0.123	12.0	3000	0.1334	0.9530
0.123	13.0	3250	0.1361	0.9540

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0