bedus-creation/mbart-small-dataset-ii-eng-to-lim-005

This model is a fine-tuned version of mbart-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 4.7245
• Validation Loss: 6.1589
• Epoch: 349

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
8.4366	7.8649	0
7.8684	7.6440	1
7.7002	7.5328	2
7.5948	7.4486	3
7.5176	7.3868	4
7.4560	7.3324	5
7.4044	7.2855	6
7.3559	7.2365	7
7.3105	7.1809	8
7.2556	7.1305	9
7.2074	7.0882	10
7.1645	7.0523	11
7.1267	7.0236	12
7.0951	6.9883	13
7.0593	6.9593	14
7.0349	6.9400	15
7.0110	6.9160	16
6.9824	6.8902	17
6.9607	6.8716	18
6.9412	6.8525	19
6.9182	6.8337	20
6.8982	6.8178	21
6.8824	6.7984	22
6.8617	6.7825	23
6.8442	6.7660	24
6.8259	6.7494	25
6.8097	6.7386	26
6.7982	6.7210	27
6.7809	6.7095	28
6.7623	6.7007	29
6.7463	6.6821	30
6.7365	6.6703	31
6.7197	6.6623	32
6.7048	6.6462	33
6.6967	6.6421	34
6.6796	6.6343	35
6.6644	6.6172	36
6.6519	6.6143	37
6.6419	6.5981	38
6.6274	6.5878	39
6.6165	6.5824	40
6.6036	6.5701	41
6.5878	6.5622	42
6.5831	6.5504	43
6.5689	6.5434	44
6.5584	6.5383	45
6.5399	6.5246	46
6.5335	6.5189	47
6.5220	6.5079	48
6.5128	6.4998	49
6.5000	6.4904	50
6.4916	6.4851	51
6.4780	6.4783	52
6.4646	6.4720	53
6.4613	6.4552	54
6.4490	6.4510	55
6.4343	6.4442	56
6.4277	6.4371	57
6.4194	6.4313	58
6.4047	6.4199	59
6.3960	6.4106	60
6.3860	6.4075	61
6.3724	6.4045	62
6.3687	6.4019	63
6.3549	6.3878	64
6.3448	6.3807	65
6.3413	6.3781	66
6.3290	6.3738	67
6.3190	6.3642	68
6.3131	6.3598	69
6.2984	6.3536	70
6.2902	6.3422	71
6.2861	6.3377	72
6.2722	6.3377	73
6.2680	6.3278	74
6.2566	6.3217	75
6.2483	6.3172	76
6.2423	6.3098	77
6.2298	6.3081	78
6.2227	6.3011	79
6.2144	6.2932	80
6.2101	6.2905	81
6.1995	6.2877	82
6.1914	6.2838	83
6.1854	6.2800	84
6.1717	6.2722	85
6.1653	6.2689	86
6.1523	6.2678	87
6.1478	6.2577	88
6.1426	6.2567	89
6.1373	6.2535	90
6.1280	6.2511	91
6.1219	6.2371	92
6.1153	6.2373	93
6.1040	6.2347	94
6.0969	6.2340	95
6.0923	6.2320	96
6.0803	6.2222	97
6.0725	6.2178	98
6.0729	6.2144	99
6.0577	6.2236	100
6.0550	6.2041	101
6.0484	6.2030	102
6.0361	6.2051	103
6.0302	6.1977	104
6.0218	6.1937	105
6.0174	6.1935	106
6.0073	6.1899	107
6.0060	6.1883	108
5.9978	6.1783	109
5.9896	6.1827	110
5.9777	6.1770	111
5.9778	6.1693	112
5.9708	6.1707	113
5.9673	6.1590	114
5.9527	6.1713	115
5.9481	6.1604	116
5.9424	6.1603	117
5.9370	6.1547	118
5.9304	6.1574	119
5.9178	6.1506	120
5.9134	6.1478	121
5.9063	6.1440	122
5.8979	6.1406	123
5.8954	6.1384	124
5.8916	6.1418	125
5.8832	6.1362	126
5.8768	6.1319	127
5.8658	6.1348	128
5.8624	6.1318	129
5.8533	6.1196	130
5.8543	6.1273	131
5.8467	6.1118	132
5.8442	6.1191	133
5.8304	6.1320	134
5.8203	6.1158	135
5.8213	6.1142	136
5.8104	6.1116	137
5.8094	6.1126	138
5.7985	6.1105	139
5.7935	6.1018	140
5.7890	6.0984	141
5.7830	6.1016	142
5.7746	6.0977	143
5.7674	6.0997	144
5.7672	6.1080	145
5.7610	6.1039	146
5.7481	6.0915	147
5.7424	6.0873	148
5.7376	6.1008	149
5.7373	6.0831	150
5.7297	6.0911	151
5.7246	6.0920	152
5.7212	6.0897	153
5.7130	6.0784	154
5.7075	6.0794	155
5.6996	6.0880	156
5.6904	6.0793	157
5.6885	6.0713	158
5.6852	6.0854	159
5.6778	6.0719	160
5.6744	6.0712	161
5.6658	6.0784	162
5.6502	6.0747	163
5.6529	6.0715	164
5.6495	6.0735	165
5.6423	6.0722	166
5.6295	6.0707	167
5.6348	6.0691	168
5.6265	6.0762	169
5.6196	6.0679	170
5.6145	6.0675	171
5.6079	6.0622	172
5.6054	6.0676	173
5.5981	6.0658	174
5.5913	6.0607	175
5.5825	6.0546	176
5.5814	6.0588	177
5.5798	6.0482	178
5.5649	6.0603	179
5.5668	6.0510	180
5.5597	6.0643	181
5.5475	6.0641	182
5.5528	6.0585	183
5.5409	6.0620	184
5.5352	6.0466	185
5.5403	6.0507	186
5.5293	6.0510	187
5.5201	6.0662	188
5.5154	6.0554	189
5.5134	6.0430	190
5.5063	6.0596	191
5.4987	6.0458	192
5.4974	6.0416	193
5.4857	6.0499	194
5.4817	6.0659	195
5.4750	6.0540	196
5.4719	6.0493	197
5.4618	6.0423	198
5.4644	6.0460	199
5.4526	6.0523	200
5.4507	6.0451	201
5.4504	6.0430	202
5.4412	6.0421	203
5.4377	6.0492	204
5.4367	6.0482	205
5.4190	6.0259	206
5.4210	6.0281	207
5.4191	6.0418	208
5.4090	6.0383	209
5.4051	6.0445	210
5.3975	6.0565	211
5.3942	6.0581	212
5.3930	6.0509	213
5.3825	6.0506	214
5.3811	6.0428	215
5.3722	6.0368	216
5.3676	6.0392	217
5.3655	6.0460	218
5.3577	6.0488	219
5.3539	6.0431	220
5.3497	6.0410	221
5.3433	6.0381	222
5.3437	6.0376	223
5.3369	6.0409	224
5.3283	6.0320	225
5.3231	6.0516	226
5.3160	6.0432	227
5.3075	6.0544	228
5.3095	6.0537	229
5.3025	6.0458	230
5.2969	6.0451	231
5.2807	6.0449	232
5.2925	6.0455	233
5.2767	6.0551	234
5.2778	6.0392	235
5.2713	6.0419	236
5.2691	6.0435	237
5.2570	6.0495	238
5.2574	6.0301	239
5.2521	6.0362	240
5.2458	6.0449	241
5.2352	6.0462	242
5.2389	6.0425	243
5.2265	6.0372	244
5.2297	6.0372	245
5.2244	6.0580	246
5.2181	6.0523	247
5.2061	6.0487	248
5.2100	6.0475	249
5.1985	6.0405	250
5.1945	6.0451	251
5.1911	6.0552	252
5.1839	6.0503	253
5.1829	6.0510	254
5.1797	6.0456	255
5.1747	6.0627	256
5.1652	6.0384	257
5.1659	6.0546	258
5.1449	6.0503	259
5.1592	6.0514	260
5.1448	6.0491	261
5.1405	6.0556	262
5.1391	6.0594	263
5.1346	6.0362	264
5.1275	6.0367	265
5.1218	6.0447	266
5.1144	6.0636	267
5.1152	6.0556	268
5.1083	6.0503	269
5.1046	6.0597	270
5.0923	6.0726	271
5.0988	6.0692	272
5.0926	6.0654	273
5.0892	6.0757	274
5.0772	6.0547	275
5.0774	6.0703	276
5.0696	6.0715	277
5.0645	6.0838	278
5.0599	6.0687	279
5.0565	6.0621	280
5.0535	6.0846	281
5.0409	6.0779	282
5.0413	6.0753	283
5.0380	6.0609	284
5.0336	6.0889	285
5.0248	6.0762	286
5.0230	6.0876	287
5.0155	6.0588	288
5.0121	6.0788	289
5.0035	6.0777	290
5.0067	6.0848	291
5.0016	6.0831	292
4.9929	6.0991	293
4.9889	6.1011	294
4.9837	6.0805	295
4.9777	6.0858	296
4.9738	6.0803	297
4.9708	6.0757	298
4.9677	6.0886	299
4.9630	6.0828	300
4.9541	6.0883	301
4.9541	6.1026	302
4.9453	6.0925	303
4.9385	6.0854	304
4.9337	6.1038	305
4.9290	6.0854	306
4.9287	6.1008	307
4.9214	6.1174	308
4.9151	6.1056	309
4.9118	6.0934	310
4.9087	6.0919	311
4.8985	6.1064	312
4.9003	6.1010	313
4.8951	6.1118	314
4.8824	6.1020	315
4.8834	6.1020	316
4.8764	6.1173	317
4.8704	6.1189	318
4.8690	6.0976	319
4.8662	6.1058	320
4.8586	6.1060	321
4.8571	6.1026	322
4.8514	6.1102	323
4.8426	6.1298	324
4.8375	6.1047	325
4.8341	6.1111	326
4.8303	6.1144	327
4.8320	6.1271	328
4.8190	6.1221	329
4.8214	6.1342	330
4.8055	6.1497	331
4.8082	6.1288	332
4.7967	6.1218	333
4.7966	6.1433	334
4.7859	6.1117	335
4.7841	6.1447	336
4.7871	6.1406	337
4.7743	6.1606	338
4.7696	6.1391	339
4.7652	6.1216	340
4.7684	6.1420	341
4.7607	6.1365	342
4.7596	6.1462	343
4.7539	6.1352	344
4.7382	6.1507	345
4.7425	6.1461	346
4.7299	6.1556	347
4.7268	6.1298	348
4.7245	6.1589	349

Framework versions

• Transformers 4.33.3
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3