distilroberta-rbm231k-ep20-2

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

• Loss: 1.1659

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: 7.3e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.19
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.6485	1.0	14644	1.5036
1.5674	2.0	29288	1.4329
1.5284	3.0	43932	1.4043
1.503	4.0	58576	1.3876
1.4735	5.0	73220	1.3594
1.4399	6.0	87864	1.3312
1.4061	7.0	102508	1.3074
1.3895	8.0	117152	1.2900
1.3691	9.0	131796	1.2749
1.3591	10.0	146440	1.2625
1.3267	11.0	161084	1.2501
1.314	12.0	175728	1.2353
1.2995	13.0	190372	1.2242
1.2888	14.0	205016	1.2136
1.2773	15.0	219660	1.2027
1.2557	16.0	234304	1.1920
1.2443	17.0	248948	1.1831
1.2449	18.0	263592	1.1776
1.2294	19.0	278236	1.1725
1.2231	20.0	292880	1.1666

Framework versions

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