pijarcandra22/t5Indo2Bali

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: 1.1069
• Validation Loss: 1.5697
• Epoch: 199

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
1.8126	1.8072	0
1.8017	1.8049	1
1.7984	1.8042	2
1.7845	1.7983	3
1.7843	1.7968	4
1.7812	1.7930	5
1.7593	1.7946	6
1.7647	1.7865	7
1.7710	1.7826	8
1.7464	1.7852	9
1.7467	1.7751	10
1.7380	1.7758	11
1.7417	1.7761	12
1.7433	1.7652	13
1.7306	1.7678	14
1.7226	1.7649	15
1.7102	1.7608	16
1.7125	1.7589	17
1.7005	1.7572	18
1.6927	1.7522	19
1.6859	1.7467	20
1.6895	1.7454	21
1.6780	1.7415	22
1.6807	1.7408	23
1.6730	1.7376	24
1.6673	1.7353	25
1.6648	1.7340	26
1.6566	1.7328	27
1.6537	1.7278	28
1.6508	1.7304	29
1.6445	1.7267	30
1.6437	1.7268	31
1.6345	1.7249	32
1.6228	1.7192	33
1.6310	1.7136	34
1.6236	1.7140	35
1.6151	1.7158	36
1.6114	1.7107	37
1.6076	1.7115	38
1.6047	1.7066	39
1.5923	1.7089	40
1.5897	1.7024	41
1.5822	1.7000	42
1.5815	1.6983	43
1.5854	1.6984	44
1.5728	1.6962	45
1.5672	1.6971	46
1.5735	1.6899	47
1.5576	1.6894	48
1.5649	1.6853	49
1.5572	1.6839	50
1.5534	1.6813	51
1.5491	1.6811	52
1.5487	1.6807	53
1.5376	1.6763	54
1.5367	1.6772	55
1.5242	1.6744	56
1.5251	1.6687	57
1.5246	1.6708	58
1.5260	1.6673	59
1.5073	1.6699	60
1.5063	1.6658	61
1.5238	1.6630	62
1.4991	1.6612	63
1.4994	1.6610	64
1.5001	1.6599	65
1.4911	1.6612	66
1.4926	1.6554	67
1.4852	1.6527	68
1.4720	1.6554	69
1.4740	1.6533	70
1.4759	1.6487	71
1.4692	1.6450	72
1.4632	1.6480	73
1.4664	1.6424	74
1.4591	1.6436	75
1.4606	1.6384	76
1.4487	1.6382	77
1.4558	1.6375	78
1.4455	1.6389	79
1.4396	1.6427	80
1.4441	1.6363	81
1.4333	1.6357	82
1.4414	1.6348	83
1.4260	1.6319	84
1.4249	1.6317	85
1.4166	1.6268	86
1.4167	1.6301	87
1.4150	1.6244	88
1.4061	1.6273	89
1.4134	1.6260	90
1.4022	1.6237	91
1.3949	1.6246	92
1.4007	1.6231	93
1.3987	1.6184	94
1.3919	1.6178	95
1.3889	1.6178	96
1.3883	1.6209	97
1.3756	1.6175	98
1.3818	1.6139	99
1.3772	1.6129	100
1.3726	1.6159	101
1.3695	1.6158	102
1.3707	1.6110	103
1.3555	1.6132	104
1.3592	1.6085	105
1.3562	1.6111	106
1.3475	1.6095	107
1.3460	1.6100	108
1.3446	1.6093	109
1.3436	1.6095	110
1.3452	1.6068	111
1.3401	1.6054	112
1.3378	1.6085	113
1.3288	1.6056	114
1.3294	1.6057	115
1.3227	1.6018	116
1.3270	1.5989	117
1.3214	1.5956	118
1.3187	1.5986	119
1.3150	1.5986	120
1.3145	1.5958	121
1.3159	1.5980	122
1.3050	1.5978	123
1.3113	1.5956	124
1.2932	1.5972	125
1.3008	1.5927	126
1.2963	1.5960	127
1.2799	1.5950	128
1.2879	1.5918	129
1.2873	1.5891	130
1.2868	1.5884	131
1.2789	1.5922	132
1.2751	1.5887	133
1.2780	1.5888	134
1.2632	1.5913	135
1.2617	1.5835	136
1.2681	1.5910	137
1.2630	1.5893	138
1.2631	1.5877	139
1.2540	1.5892	140
1.2518	1.5812	141
1.2611	1.5812	142
1.2561	1.5808	143
1.2483	1.5757	144
1.2424	1.5785	145
1.2366	1.5806	146
1.2393	1.5801	147
1.2359	1.5781	148
1.2256	1.5796	149
1.2261	1.5818	150
1.2179	1.5782	151
1.2321	1.5720	152
1.2198	1.5744	153
1.2189	1.5780	154
1.2301	1.5747	155
1.2131	1.5776	156
1.2095	1.5746	157
1.2134	1.5756	158
1.2061	1.5761	159
1.2068	1.5727	160
1.2061	1.5714	161
1.1998	1.5756	162
1.1967	1.5780	163
1.1940	1.5747	164
1.1869	1.5713	165
1.1980	1.5700	166
1.1958	1.5714	167
1.1867	1.5666	168
1.1779	1.5715	169
1.1789	1.5765	170
1.1763	1.5742	171
1.1767	1.5708	172
1.1840	1.5682	173
1.1688	1.5747	174
1.1701	1.5696	175
1.1739	1.5658	176
1.1572	1.5688	177
1.1593	1.5659	178
1.1591	1.5684	179
1.1581	1.5644	180
1.1635	1.5655	181
1.1538	1.5662	182
1.1455	1.5666	183
1.1442	1.5650	184
1.1398	1.5668	185
1.1408	1.5712	186
1.1364	1.5679	187
1.1348	1.5653	188
1.1358	1.5704	189
1.1355	1.5652	190
1.1278	1.5650	191
1.1260	1.5697	192
1.1257	1.5686	193
1.1265	1.5712	194
1.1248	1.5625	195
1.1220	1.5704	196
1.1202	1.5666	197
1.1114	1.5653	198
1.1069	1.5697	199

Framework versions

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