roberta-base-finetuned-recruitment-eval-2

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

• Loss: 0.1002
• Precision: 0.8023
• Recall: 0.8531
• F1: 0.8269
• Accuracy: 0.9760

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	15	0.3547	0.0	0.0	0.0	0.9127
No log	2.0	30	0.2395	0.3442	0.2978	0.3194	0.9305
No log	3.0	45	0.1640	0.5315	0.6253	0.5746	0.9576
No log	4.0	60	0.1231	0.6518	0.7871	0.7131	0.9606
No log	5.0	75	0.1076	0.7409	0.8208	0.7788	0.9708
No log	6.0	90	0.1220	0.6817	0.8342	0.7503	0.9658
No log	7.0	105	0.1030	0.7850	0.8167	0.8005	0.9757
No log	8.0	120	0.1053	0.7769	0.8167	0.7963	0.9745
No log	9.0	135	0.1002	0.8023	0.8531	0.8269	0.9760
No log	10.0	150	0.1100	0.7689	0.8477	0.8064	0.9724
No log	11.0	165	0.1061	0.7757	0.8531	0.8126	0.9731
No log	12.0	180	0.1081	0.7748	0.8531	0.8121	0.9734
No log	13.0	195	0.1095	0.7761	0.8504	0.8116	0.9737
No log	14.0	210	0.1124	0.7800	0.8504	0.8137	0.9743
No log	15.0	225	0.1117	0.7800	0.8504	0.8137	0.9746

Framework versions

• Transformers 4.27.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3