metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: pijarcandra22/t5Indo2Jawa
    results: []

pijarcandra22/t5Indo2Jawa

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: 1.4387
Validation Loss: 1.4507
Epoch: 177

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
3.5149	3.1567	0
3.3816	3.0397	1
3.2812	2.9518	2
3.1977	2.8751	3
3.1223	2.8078	4
3.0599	2.7507	5
3.0019	2.6979	6
2.9517	2.6513	7
2.9034	2.6121	8
2.8638	2.5756	9
2.8232	2.5391	10
2.7856	2.5089	11
2.7541	2.4786	12
2.7219	2.4499	13
2.6935	2.4256	14
2.6658	2.4010	15
2.6389	2.3762	16
2.6143	2.3550	17
2.5899	2.3313	18
2.5665	2.3156	19
2.5445	2.2939	20
2.5224	2.2750	21
2.5022	2.2569	22
2.4834	2.2410	23
2.4641	2.2220	24
2.4443	2.2091	25
2.4267	2.1948	26
2.4129	2.1796	27
2.3937	2.1657	28
2.3782	2.1523	29
2.3616	2.1385	30
2.3471	2.1267	31
2.3351	2.1110	32
2.3184	2.0988	33
2.3047	2.0871	34
2.2920	2.0768	35
2.2767	2.0649	36
2.2651	2.0546	37
2.2526	2.0445	38
2.2388	2.0333	39
2.2264	2.0234	40
2.2157	2.0165	41
2.2050	2.0049	42
2.1906	1.9946	43
2.1824	1.9845	44
2.1673	1.9762	45
2.1559	1.9679	46
2.1455	1.9608	47
2.1377	1.9528	48
2.1279	1.9429	49
2.1176	1.9356	50
2.1056	1.9267	51
2.0979	1.9174	52
2.0882	1.9087	53
2.0802	1.8995	54
2.0668	1.8947	55
2.0597	1.8880	56
2.0484	1.8779	57
2.0405	1.8735	58
2.0335	1.8676	59
2.0254	1.8603	60
2.0147	1.8530	61
2.0078	1.8459	62
1.9984	1.8403	63
1.9902	1.8338	64
1.9824	1.8264	65
1.9768	1.8231	66
1.9679	1.8158	67
1.9597	1.8104	68
1.9531	1.8026	69
1.9460	1.7987	70
1.9416	1.7929	71
1.9291	1.7876	72
1.9245	1.7807	73
1.9143	1.7788	74
1.9088	1.7717	75
1.9006	1.7643	76
1.8960	1.7587	77
1.8901	1.7528	78
1.8808	1.7477	79
1.8740	1.7436	80
1.8689	1.7376	81
1.8628	1.7320	82
1.8533	1.7312	83
1.8486	1.7240	84
1.8428	1.7186	85
1.8351	1.7141	86
1.8316	1.7106	87
1.8234	1.7045	88
1.8173	1.6976	89
1.8109	1.6959	90
1.8059	1.6924	91
1.8016	1.6860	92
1.7922	1.6802	93
1.7887	1.6778	94
1.7832	1.6716	95
1.7761	1.6688	96
1.7724	1.6653	97
1.7662	1.6582	98
1.7607	1.6571	99
1.7549	1.6542	100
1.7483	1.6497	101
1.7454	1.6435	102
1.7400	1.6407	103
1.7318	1.6363	104
1.7266	1.6327	105
1.7234	1.6286	106
1.7210	1.6267	107
1.7109	1.6207	108
1.7079	1.6183	109
1.7026	1.6162	110
1.6989	1.6137	111
1.6925	1.6074	112
1.6880	1.6051	113
1.6823	1.6021	114
1.6780	1.5969	115
1.6737	1.5960	116
1.6659	1.5937	117
1.6603	1.5872	118
1.6586	1.5870	119
1.6550	1.5813	120
1.6506	1.5788	121
1.6432	1.5771	122
1.6408	1.5721	123
1.6377	1.5729	124
1.6307	1.5693	125
1.6268	1.5650	126
1.6227	1.5607	127
1.6180	1.5618	128
1.6151	1.5590	129
1.6101	1.5534	130
1.6056	1.5505	131
1.6034	1.5470	132
1.5971	1.5443	133
1.5926	1.5431	134
1.5873	1.5421	135
1.5850	1.5378	136
1.5807	1.5334	137
1.5771	1.5335	138
1.5734	1.5309	139
1.5694	1.5288	140
1.5642	1.5273	141
1.5610	1.5215	142
1.5568	1.5217	143
1.5555	1.5171	144
1.5517	1.5170	145
1.5471	1.5148	146
1.5426	1.5120	147
1.5376	1.5102	148
1.5370	1.5081	149
1.5317	1.5070	150
1.5272	1.5029	151
1.5257	1.5025	152
1.5205	1.4997	153
1.5180	1.4954	154
1.5112	1.4932	155
1.5117	1.4920	156
1.5070	1.4890	157
1.5050	1.4881	158
1.4984	1.4870	159
1.4964	1.4843	160
1.4920	1.4833	161
1.4879	1.4808	162
1.4838	1.4768	163
1.4854	1.4756	164
1.4784	1.4733	165
1.4757	1.4724	166
1.4733	1.4697	167
1.4704	1.4678	168
1.4660	1.4648	169
1.4618	1.4660	170
1.4591	1.4606	171
1.4554	1.4626	172
1.4533	1.4595	173
1.4492	1.4583	174
1.4471	1.4539	175
1.4410	1.4548	176
1.4387	1.4507	177

Framework versions

Transformers 4.35.2
TensorFlow 2.14.0
Datasets 2.15.0
Tokenizers 0.15.0