metadata

license: apache-2.0
base_model: mnaylor/mega-base-wikitext
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mega-base-wikitext-finetuned-INCIBE
    results: []

mega-base-wikitext-finetuned-INCIBE

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

Loss: 1.5428
Accuracy: 0.3760

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	196	1.8660	0.2296
No log	2.0	392	1.7639	0.2457
1.9099	3.0	588	1.7296	0.2528
1.9099	4.0	784	1.7125	0.2547
1.9099	5.0	980	1.7017	0.2595
1.7129	6.0	1176	1.6944	0.2946
1.7129	7.0	1372	1.6882	0.2872
1.6904	8.0	1568	1.6827	0.2830
1.6904	9.0	1764	1.6742	0.3204
1.6904	10.0	1960	1.6570	0.3312
1.6668	11.0	2156	1.6293	0.3514
1.6668	12.0	2352	1.6035	0.3555
1.6166	13.0	2548	1.5813	0.3607
1.6166	14.0	2744	1.5664	0.3671
1.6166	15.0	2940	1.5578	0.3715
1.5574	16.0	3136	1.5547	0.3715
1.5574	17.0	3332	1.5444	0.3738
1.5278	18.0	3528	1.5429	0.3760
1.5278	19.0	3724	1.5402	0.3757
1.5278	20.0	3920	1.5384	0.3738
1.5141	21.0	4116	1.5351	0.3745
1.5141	22.0	4312	1.5373	0.3738
1.5091	23.0	4508	1.5356	0.3715
1.5091	24.0	4704	1.5353	0.3730
1.5091	25.0	4900	1.5349	0.3734

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3