README.md

metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: pijarcandra22/NMTIndoBaliT5
    results: []

pijarcandra22/NMTIndoBaliT5

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.8952
• Validation Loss: 1.3812
• Epoch: 49

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': 1e-04, '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
3.2881	2.6852	0
2.7514	2.4004	1
2.5012	2.2171	2
2.3252	2.0959	3
2.1930	1.9901	4
2.0837	1.9130	5
1.9912	1.8452	6
1.9107	1.7974	7
1.8459	1.7521	8
1.7902	1.7165	9
1.7321	1.6842	10
1.6811	1.6400	11
1.6374	1.6230	12
1.5973	1.5960	13
1.5588	1.5765	14
1.5244	1.5589	15
1.4933	1.5370	16
1.4588	1.5300	17
1.4325	1.5107	18
1.4054	1.4970	19
1.3730	1.4839	20
1.3475	1.4789	21
1.3231	1.4616	22
1.3035	1.4568	23
1.2768	1.4489	24
1.2587	1.4396	25
1.2380	1.4364	26
1.2208	1.4273	27
1.2026	1.4228	28
1.1755	1.4141	29
1.1614	1.4062	30
1.1460	1.4060	31
1.1289	1.3934	32
1.1134	1.4007	33
1.0965	1.3927	34
1.0818	1.3874	35
1.0661	1.3921	36
1.0482	1.3795	37
1.0345	1.3853	38
1.0195	1.3835	39
1.0074	1.3772	40
0.9890	1.3851	41
0.9833	1.3724	42
0.9667	1.3740	43
0.9561	1.3752	44
0.9429	1.3673	45
0.9301	1.3828	46
0.9141	1.3806	47
0.9050	1.3772	48
0.8952	1.3812	49

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2