metadata

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

roberta-base-riddle-finetuned_new

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

Loss: 0.3192
Accuracy: 0.8500

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: 0.0005
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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	23	0.4749	0.75
No log	2.0	46	0.4396	0.7750
No log	3.0	69	0.4988	0.7750
No log	4.0	92	0.4534	0.8000
No log	5.0	115	0.4505	0.8250
No log	6.0	138	0.4108	0.8250
No log	7.0	161	0.4701	0.8000
No log	8.0	184	0.4327	0.8250
No log	9.0	207	0.5293	0.8000
No log	10.0	230	0.5596	0.7750
No log	11.0	253	0.4872	0.9000
No log	12.0	276	0.3860	0.8500
No log	13.0	299	0.4549	0.9000
No log	14.0	322	0.4340	0.8250
No log	15.0	345	0.4540	0.7750
No log	16.0	368	0.5259	0.75
No log	17.0	391	0.3192	0.8500
No log	18.0	414	0.3699	0.875
No log	19.0	437	0.3577	0.875
No log	20.0	460	0.4405	0.8250
No log	21.0	483	0.5207	0.8250
0.1396	22.0	506	0.4686	0.8000
0.1396	23.0	529	0.4614	0.875
0.1396	24.0	552	0.4442	0.8250
0.1396	25.0	575	0.4242	0.8250
0.1396	26.0	598	0.4943	0.8000
0.1396	27.0	621	0.4973	0.8500
0.1396	28.0	644	0.4542	0.875
0.1396	29.0	667	0.4671	0.875
0.1396	30.0	690	0.4679	0.875

Framework versions

Transformers 4.36.2
Pytorch 1.13.1+cu117
Datasets 2.16.1
Tokenizers 0.15.0