README.md

metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: pijarcandra22/t5Indo2Sunda
    results: []

pijarcandra22/t5Indo2Sunda

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: 2.5165
• Validation Loss: 2.3592
• Epoch: 46

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
4.3724	3.9124	0
3.9887	3.6348	1
3.7534	3.4215	2
3.5819	3.2847	3
3.4632	3.1902	4
3.3751	3.1139	5
3.3039	3.0493	6
3.2447	2.9955	7
3.1911	2.9481	8
3.1455	2.9082	9
3.1068	2.8718	10
3.0697	2.8387	11
3.0381	2.8105	12
3.0050	2.7825	13
2.9796	2.7568	14
2.9510	2.7350	15
2.9259	2.7096	16
2.9053	2.6881	17
2.8833	2.6696	18
2.8599	2.6510	19
2.8403	2.6328	20
2.8207	2.6171	21
2.8046	2.5999	22
2.7861	2.5857	23
2.7715	2.5699	24
2.7557	2.5542	25
2.7387	2.5420	26
2.7225	2.5299	27
2.7085	2.5182	28
2.6950	2.5081	29
2.6818	2.4951	30
2.6687	2.4864	31
2.6578	2.4760	32
2.6461	2.4651	33
2.6334	2.4559	34
2.6213	2.4477	35
2.6096	2.4373	36
2.5993	2.4297	37
2.5906	2.4208	38
2.5778	2.4100	39
2.5703	2.4025	40
2.5594	2.3962	41
2.5521	2.3901	42
2.5414	2.3808	43
2.5318	2.3726	44
2.5235	2.3684	45
2.5165	2.3592	46

Framework versions

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