README.md

metadata

license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: NLP_Capstone
    results: []

NLP_Capstone

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

• Loss: 0.3184
• Accuracy: 0.9131

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4675	0.2	500	0.3681	0.8803
0.3759	0.4	1000	0.5198	0.8721
0.3657	0.6	1500	0.3482	0.9040
0.3139	0.8	2000	0.3184	0.9131
0.3442	1.0	2500	0.3415	0.9058
0.2745	1.2	3000	0.3522	0.8745
0.2413	1.41	3500	0.3306	0.9105
0.2517	1.61	4000	0.3334	0.9243
0.2499	1.81	4500	0.3907	0.9072
0.2473	2.01	5000	0.3441	0.9229
0.1608	2.21	5500	0.3697	0.9187
0.173	2.41	6000	0.3362	0.9225
0.1749	2.61	6500	0.3591	0.9237
0.1725	2.81	7000	0.4014	0.9255
0.1616	3.01	7500	0.3456	0.9271
0.1047	3.21	8000	0.3773	0.9285
0.1062	3.41	8500	0.3980	0.9217
0.1029	3.61	9000	0.3808	0.9293
0.1004	3.81	9500	0.3696	0.9289
0.0822	4.01	10000	0.3950	0.9309
0.0408	4.22	10500	0.4388	0.9285
0.0643	4.42	11000	0.4204	0.9285
0.0536	4.62	11500	0.4102	0.9301
0.0508	4.82	12000	0.4139	0.9297

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1