xlm-roberta-base-finetuned-ANAD-mlm-0.15-base-19OCT

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

• Loss: 1.5208

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-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
2.0052	0.9999	1063	1.8141
1.9038	1.9999	2126	1.7297
1.8271	2.9998	3189	1.6728
1.7734	3.9998	4252	1.6329
1.728	4.9997	5315	1.6055
1.6905	5.9996	6378	1.5794
1.6624	6.9996	7441	1.5558
1.6257	7.9995	8504	1.5368
1.6127	8.9995	9567	1.5279
1.593	9.9994	10630	1.5208

Framework versions

• Transformers 4.43.4
• Pytorch 2.1.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1