metadata

license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_keras_callback
model-index:
  - name: pijarcandra22/BartIndo2Bali
    results: []

pijarcandra22/BartIndo2Bali

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: 0.5907
Validation Loss: 2.2176
Epoch: 51

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
4.3767	3.6194	0
3.5364	3.1996	1
3.1525	2.9458	2
2.8777	2.8118	3
2.6993	2.6979	4
2.5550	2.6071	5
2.4536	2.5362	6
2.3338	2.4572	7
2.2394	2.3878	8
2.1466	2.3692	9
2.0795	2.3189	10
2.0061	2.2674	11
1.9321	2.2393	12
1.8837	2.2181	13
1.8224	2.2002	14
1.7626	2.1671	15
1.7251	2.1386	16
1.6624	2.1245	17
1.6191	2.1134	18
1.6177	2.1061	19
1.5524	2.0845	20
1.4965	2.0750	21
1.4618	2.0527	22
1.4188	2.0584	23
1.3774	2.0359	24
1.3469	2.0567	25
1.3113	2.0295	26
1.2791	2.0134	27
1.2436	2.0431	28
1.1915	2.0201	29
1.1815	2.0283	30
1.1314	2.0230	31
1.1071	2.0424	32
1.0781	2.0357	33
1.0429	2.0208	34
1.0134	2.0458	35
0.9799	2.0466	36
0.9567	2.0592	37
0.9261	2.0278	38
0.8931	2.0641	39
0.8742	2.0783	40
0.8397	2.0781	41
0.8228	2.1010	42
0.7819	2.1042	43
0.7667	2.1302	44
0.7508	2.1193	45
0.7136	2.1372	46
0.6849	2.1513	47
0.6625	2.1747	48
0.6451	2.1936	49
0.6114	2.1650	50
0.5907	2.2176	51

Framework versions

Transformers 4.35.2
TensorFlow 2.14.0
Datasets 2.15.0
Tokenizers 0.15.0