metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: beit-base-patch16-224
    results: []

beit-base-patch16-224

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5338
Accuracy: 0.7165
Precision: 0.7127
Recall: 0.7165
F1 Score: 0.7139

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: 48
eval_batch_size: 48
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 192
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 45

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 Score
No log	0.8	2	0.7127	0.5686	0.3992	0.5686	0.4691
No log	2.0	5	0.5967	0.6863	0.7053	0.6863	0.6139
No log	2.8	7	0.5384	0.7843	0.7801	0.7843	0.7792
No log	4.0	10	0.6429	0.6078	0.6547	0.6078	0.6164
No log	4.8	12	0.6321	0.7255	0.7205	0.7255	0.7011
No log	6.0	15	0.6473	0.7255	0.7164	0.7255	0.7095
No log	6.8	17	0.7575	0.6863	0.6694	0.6863	0.6584
No log	8.0	20	0.9926	0.7255	0.7312	0.7255	0.6908
No log	8.8	22	0.9139	0.7255	0.7205	0.7255	0.7011
No log	10.0	25	1.0884	0.7059	0.6937	0.7059	0.6845
No log	10.8	27	1.2796	0.7451	0.7521	0.7451	0.7179
0.287	12.0	30	1.3326	0.6863	0.6704	0.6863	0.6680
0.287	12.8	32	1.5649	0.7255	0.7205	0.7255	0.7011
0.287	14.0	35	1.7452	0.7255	0.7205	0.7255	0.7011
0.287	14.8	37	1.7826	0.7255	0.7205	0.7255	0.7011
0.287	16.0	40	1.9538	0.7255	0.7312	0.7255	0.6908
0.287	16.8	42	1.8850	0.6863	0.6694	0.6863	0.6584
0.287	18.0	45	1.7633	0.6863	0.6739	0.6863	0.6756
0.287	18.8	47	1.7925	0.7059	0.6940	0.7059	0.6925
0.287	20.0	50	2.1156	0.7255	0.7312	0.7255	0.6908
0.287	20.8	52	2.0156	0.7255	0.7205	0.7255	0.7011
0.287	22.0	55	1.8471	0.7255	0.7164	0.7255	0.7095
0.287	22.8	57	1.7831	0.7647	0.7593	0.7647	0.7567
0.0041	24.0	60	1.7628	0.7647	0.7593	0.7647	0.7567
0.0041	24.8	62	1.8077	0.7451	0.7382	0.7451	0.7335
0.0041	26.0	65	1.8068	0.7843	0.7823	0.7843	0.7745
0.0041	26.8	67	1.7925	0.7647	0.7593	0.7647	0.7567
0.0041	28.0	70	1.7721	0.7843	0.7823	0.7843	0.7745
0.0041	28.8	72	1.7919	0.7647	0.7624	0.7647	0.7510
0.0041	30.0	75	1.9588	0.7451	0.7521	0.7451	0.7179
0.0041	30.8	77	1.9200	0.7451	0.7521	0.7451	0.7179
0.0041	32.0	80	1.7746	0.7451	0.7521	0.7451	0.7179
0.0041	32.8	82	1.7253	0.7647	0.7624	0.7647	0.7510
0.0041	34.0	85	1.6992	0.7451	0.7382	0.7451	0.7335
0.0041	34.8	87	1.6938	0.7451	0.7382	0.7451	0.7335
0.0031	36.0	90	1.7014	0.7451	0.7382	0.7451	0.7335

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2