rh_qa_model

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

• Loss: 2.0857

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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	9	5.4568
No log	2.0	18	4.7897
No log	3.0	27	4.6445
No log	4.0	36	3.9367
No log	5.0	45	3.4457
No log	6.0	54	3.3149
No log	7.0	63	2.6427
No log	8.0	72	2.6698
No log	9.0	81	2.2418
No log	10.0	90	2.3653
No log	11.0	99	2.1887
No log	12.0	108	2.1629
No log	13.0	117	2.2699
No log	14.0	126	2.1080
No log	15.0	135	2.1836
No log	16.0	144	2.0967
No log	17.0	153	2.1418
No log	18.0	162	2.0863
No log	19.0	171	2.0778
No log	20.0	180	2.0857

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1