metadata

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

roberta-base_brkfst_trainer

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

Loss: 0.0782
Accuracy: 0.98

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: 32
eval_batch_size: 32
seed: 27
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	Accuracy
0.6559	0.71	10	0.6907	0.8
0.5465	1.43	20	0.3822	0.84
0.4035	2.14	30	0.3178	0.93
0.3651	2.86	40	0.1117	0.94
0.1986	3.57	50	0.1832	0.95
0.2985	4.29	60	0.1133	0.96
0.141	5.0	70	0.1594	0.97
0.1334	5.71	80	0.2771	0.96
0.1874	6.43	90	0.0757	0.95
0.0594	7.14	100	0.2082	0.95
0.2883	7.86	110	0.2366	0.96
0.0459	8.57	120	0.1599	0.96
0.0733	9.29	130	0.2568	0.96
0.0483	10.0	140	0.3639	0.94
0.0487	10.71	150	0.2121	0.97
0.0339	11.43	160	0.1368	0.98
0.0463	12.14	170	0.1465	0.98
0.0025	12.86	180	0.2487	0.96
0.0009	13.57	190	0.0968	0.98
0.0003	14.29	200	0.0710	0.98
0.0003	15.0	210	0.0782	0.98

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2