bedus-creation/eng-limbu-t5-large-all-002

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: 1.8999
• Validation Loss: 2.7328
• Epoch: 279

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
7.7953	7.0449	0
7.0758	6.6946	1
6.7576	6.5212	2
6.5967	6.3865	3
6.4694	6.2904	4
6.3887	6.2178	5
6.2966	6.1474	6
6.2517	6.0932	7
6.1860	6.0366	8
6.1346	5.9946	9
6.0712	5.9387	10
6.0509	5.9157	11
6.0028	5.8848	12
5.9767	5.8508	13
5.9447	5.8147	14
5.8854	5.7756	15
5.8718	5.7431	16
5.8380	5.7119	17
5.8139	5.6781	18
5.7940	5.6455	19
5.7526	5.6239	20
5.7284	5.5838	21
5.6846	5.5729	22
5.6370	5.5342	23
5.6364	5.4946	24
5.5995	5.4774	25
5.5687	5.4367	26
5.5542	5.4143	27
5.5180	5.3827	28
5.4891	5.3586	29
5.4495	5.3369	30
5.4378	5.3089	31
5.4178	5.2933	32
5.4018	5.2644	33
5.3636	5.2449	34
5.3411	5.2251	35
5.2948	5.1966	36
5.2743	5.1697	37
5.2674	5.1476	38
5.2382	5.1407	39
5.2198	5.1172	40
5.1973	5.0913	41
5.1627	5.0737	42
5.1588	5.0510	43
5.1127	5.0454	44
5.0878	5.0105	45
5.0613	5.0046	46
5.0591	4.9855	47
5.0412	4.9752	48
4.9854	4.9594	49
4.9747	4.9363	50
4.9700	4.9218	51
4.9462	4.9077	52
4.9262	4.8845	53
4.9259	4.8694	54
4.8775	4.8454	55
4.8740	4.8548	56
4.8358	4.8191	57
4.8322	4.8062	58
4.7923	4.7926	59
4.7962	4.7772	60
4.7558	4.7718	61
4.7590	4.7415	62
4.7218	4.7336	63
4.7066	4.7259	64
4.6890	4.7041	65
4.6694	4.7048	66
4.6403	4.6774	67
4.6289	4.6763	68
4.6279	4.6538	69
4.6049	4.6313	70
4.5677	4.6278	71
4.5795	4.6051	72
4.5540	4.5965	73
4.5160	4.5783	74
4.5139	4.5696	75
4.5000	4.5461	76
4.4890	4.5406	77
4.4287	4.5367	78
4.4327	4.5103	79
4.4258	4.4959	80
4.4061	4.4783	81
4.3990	4.4655	82
4.3895	4.4568	83
4.3561	4.4437	84
4.3408	4.4307	85
4.3202	4.4179	86
4.2858	4.4040	87
4.2933	4.4001	88
4.2824	4.3876	89
4.2461	4.3682	90
4.2468	4.3575	91
4.2210	4.3480	92
4.2108	4.3273	93
4.1970	4.3143	94
4.1821	4.3085	95
4.1640	4.2918	96
4.1481	4.2699	97
4.1312	4.2643	98
4.1221	4.2473	99
4.1146	4.2410	100
4.0680	4.2203	101
4.0452	4.2196	102
4.0217	4.2066	103
4.0366	4.2025	104
4.0123	4.1800	105
3.9836	4.1794	106
3.9713	4.1535	107
3.9780	4.1415	108
3.9404	4.1295	109
3.9220	4.1263	110
3.9356	4.1115	111
3.8844	4.0967	112
3.8773	4.0870	113
3.8716	4.0853	114
3.8412	4.0683	115
3.8377	4.0502	116
3.8244	4.0485	117
3.8084	4.0419	118
3.8034	4.0267	119
3.7625	4.0202	120
3.7533	4.0012	121
3.7537	3.9910	122
3.7306	3.9875	123
3.7285	3.9704	124
3.7029	3.9639	125
3.6878	3.9554	126
3.6739	3.9437	127
3.6867	3.9331	128
3.6416	3.9241	129
3.6223	3.9166	130
3.6140	3.9054	131
3.6078	3.8965	132
3.5949	3.8874	133
3.5544	3.8686	134
3.5501	3.8648	135
3.5556	3.8563	136
3.5244	3.8394	137
3.4931	3.8349	138
3.4979	3.8258	139
3.4661	3.8151	140
3.4753	3.7984	141
3.4504	3.7964	142
3.4576	3.7955	143
3.4260	3.7821	144
3.4178	3.7637	145
3.3994	3.7522	146
3.3944	3.7481	147
3.3643	3.7424	148
3.3789	3.7233	149
3.3367	3.7110	150
3.3153	3.7045	151
3.3118	3.6975	152
3.3088	3.6891	153
3.2876	3.6760	154
3.2608	3.6659	155
3.2618	3.6630	156
3.2502	3.6473	157
3.2326	3.6375	158
3.2107	3.6316	159
3.1976	3.6233	160
3.1935	3.6101	161
3.1789	3.6092	162
3.1475	3.6092	163
3.1672	3.5901	164
3.1377	3.5858	165
3.1281	3.5749	166
3.1049	3.5581	167
3.0839	3.5556	168
3.0851	3.5453	169
3.0769	3.5320	170
3.0775	3.5266	171
3.0284	3.5204	172
3.0525	3.5146	173
3.0226	3.5012	174
2.9960	3.4935	175
2.9902	3.4852	176
2.9843	3.4776	177
2.9690	3.4626	178
2.9569	3.4593	179
2.9346	3.4547	180
2.9186	3.4286	181
2.9128	3.4255	182
2.9268	3.4247	183
2.9021	3.4132	184
2.8866	3.4039	185
2.8667	3.4000	186
2.8837	3.3907	187
2.8454	3.3769	188
2.8227	3.3815	189
2.8175	3.3662	190
2.8069	3.3581	191
2.7910	3.3586	192
2.7819	3.3428	193
2.7717	3.3350	194
2.7649	3.3186	195
2.7390	3.3211	196
2.7235	3.3040	197
2.7286	3.2991	198
2.7103	3.2952	199
2.7014	3.2773	200
2.6868	3.2711	201
2.6902	3.2669	202
2.6576	3.2577	203
2.6249	3.2544	204
2.6401	3.2438	205
2.6318	3.2227	206
2.6323	3.2356	207
2.6169	3.2217	208
2.6088	3.2107	209
2.5782	3.2105	210
2.5698	3.2004	211
2.5615	3.1989	212
2.5591	3.1856	213
2.5351	3.1888	214
2.5340	3.1684	215
2.5246	3.1591	216
2.5193	3.1515	217
2.4921	3.1439	218
2.4864	3.1377	219
2.4649	3.1273	220
2.4677	3.1305	221
2.4673	3.1219	222
2.4337	3.1115	223
2.4299	3.1004	224
2.3988	3.0971	225
2.4104	3.0896	226
2.4033	3.0806	227
2.3804	3.0762	228
2.3520	3.0737	229
2.3598	3.0566	230
2.3498	3.0555	231
2.3629	3.0408	232
2.3383	3.0410	233
2.3226	3.0288	234
2.3126	3.0275	235
2.3112	3.0293	236
2.2838	3.0065	237
2.2786	2.9994	238
2.2599	2.9986	239
2.2481	2.9894	240
2.2472	2.9854	241
2.2187	2.9790	242
2.2278	2.9645	243
2.2268	2.9652	244
2.2018	2.9571	245
2.1895	2.9434	246
2.1744	2.9463	247
2.1717	2.9351	248
2.1529	2.9302	249
2.1614	2.9310	250
2.1574	2.9184	251
2.1357	2.9118	252
2.1349	2.9017	253
2.1102	2.8898	254
2.1137	2.8973	255
2.0954	2.8839	256
2.0988	2.8771	257
2.0826	2.8695	258
2.0792	2.8674	259
2.0666	2.8579	260
2.0672	2.8475	261
2.0357	2.8424	262
2.0348	2.8343	263
2.0250	2.8397	264
2.0141	2.8213	265
2.0042	2.8273	266
2.0160	2.8118	267
1.9873	2.8120	268
1.9815	2.7944	269
1.9853	2.7964	270
1.9556	2.7879	271
1.9385	2.7821	272
1.9195	2.7754	273
1.9332	2.7688	274
1.9269	2.7578	275
1.9224	2.7474	276
1.9158	2.7407	277
1.9042	2.7362	278
1.8999	2.7328	279

Framework versions

• Transformers 4.33.2
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3