metadata

license: mit
base_model: indobenchmark/indobert-base-p2
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: gacha_model
    results: []

gacha_model

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5789
Accuracy: 0.8089
F1: 0.8065
Precision: 0.8115
Recall: 0.8052

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.23	50	0.5084	0.7739	0.7737	0.7826	0.7790
No log	0.47	100	0.4663	0.7972	0.7967	0.7964	0.7971
No log	0.7	150	0.4834	0.8112	0.8094	0.8125	0.8082
No log	0.93	200	0.4445	0.8135	0.8104	0.8194	0.8087
No log	1.16	250	0.6506	0.7879	0.7786	0.8149	0.7781
No log	1.4	300	0.5314	0.7692	0.7687	0.7810	0.7752
No log	1.63	350	0.5149	0.8065	0.8021	0.8167	0.8003
No log	1.86	400	0.4735	0.8298	0.8289	0.8296	0.8284
No log	2.09	450	0.5093	0.8275	0.8262	0.8280	0.8253
0.3338	2.33	500	0.5789	0.8089	0.8065	0.8115	0.8052
0.3338	2.56	550	0.6539	0.8065	0.8059	0.8057	0.8062
0.3338	2.79	600	0.6995	0.8042	0.8018	0.8068	0.8005
0.3338	3.02	650	0.8298	0.8182	0.8168	0.8186	0.8160
0.3338	3.26	700	0.7829	0.8089	0.8077	0.8085	0.8072
0.3338	3.49	750	0.7700	0.8205	0.8195	0.8202	0.8191
0.3338	3.72	800	0.9060	0.8089	0.8057	0.8145	0.8040
0.3338	3.95	850	0.9478	0.8112	0.8072	0.8205	0.8053
0.3338	4.19	900	0.9171	0.8089	0.8067	0.8109	0.8054
0.3338	4.42	950	0.9512	0.8065	0.8043	0.8088	0.8030
0.079	4.65	1000	0.9579	0.8065	0.8047	0.8078	0.8035
0.079	4.88	1050	0.9471	0.8089	0.8073	0.8095	0.8063

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0