pijarcandra22/BartBali2Indo

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

• Train Loss: 0.0023
• Validation Loss: 2.8624
• Epoch: 56

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.0020	2.8075	0
0.0024	2.8006	1
0.0027	2.8418	2
0.0021	2.8171	3
0.0023	2.7964	4
0.0027	2.8319	5
0.0018	2.8167	6
0.0022	2.8269	7
0.0021	2.8194	8
0.0020	2.8213	9
0.0018	2.8459	10
0.0022	2.8367	11
0.0018	2.7985	12
0.0019	2.8249	13
0.0026	2.8372	14
0.0024	2.8388	15
0.0023	2.8350	16
0.0023	2.8429	17
0.0024	2.7952	18
0.0028	2.7758	19
0.0025	2.8287	20
0.0025	2.8150	21
0.0030	2.8394	22
0.0019	2.7969	23
0.0018	2.8244	24
0.0026	2.8472	25
0.0017	2.8750	26
0.0021	2.8316	27
0.0018	2.8080	28
0.0018	2.8333	29
0.0031	2.8716	30
0.0024	2.8551	31
0.0027	2.8611	32
0.0031	2.8276	33
0.0030	2.8264	34
0.0025	2.8764	35
0.0023	2.8492	36
0.0037	2.8445	37
0.0024	2.8607	38
0.0024	2.8460	39
0.0021	2.8844	40
0.0031	2.8310	41
0.0031	2.8714	42
0.0034	2.8768	43
0.0028	2.8641	44
0.0023	2.8253	45
0.0025	2.8205	46
0.0024	2.8318	47
0.0019	2.8558	48
0.0017	2.8302	49
0.0017	2.8587	50
0.0021	2.8501	51
0.0019	2.8433	52
0.0017	2.8747	53
0.0021	2.8454	54
0.0018	2.8685	55
0.0023	2.8624	56

Framework versions

• Transformers 4.35.2
• TensorFlow 2.14.0
• Datasets 2.15.0
• Tokenizers 0.15.0