roberta_crf_ner_finetuned

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

• Loss: nan
• Precision: 0.7893
• Recall: 0.6294
• F1: 0.6950
• Accuracy: 0.8037

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0	1.0	85	nan	1.0	0.0	0.0	0.7707
0.0	2.0	170	nan	0.5437	0.1932	0.1694	0.8848
0.0	3.0	255	nan	0.4412	0.3360	0.3230	0.9228
0.0	4.0	340	nan	0.4888	0.6412	0.5523	0.9161
0.0	5.0	425	nan	0.6312	0.6266	0.6206	0.9451
0.0	6.0	510	nan	0.6319	0.6851	0.6560	0.9484
0.0	7.0	595	nan	0.6655	0.7110	0.6869	0.9518
0.0	8.0	680	nan	0.6341	0.7094	0.6693	0.9508
0.0	9.0	765	nan	0.6745	0.7127	0.6924	0.9533
0.0	10.0	850	nan	0.6886	0.7175	0.7019	0.9548

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1