Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9299	0.02	200	0.8468	0.6277
0.7967	0.03	400	0.7425	0.6855
0.7497	0.05	600	0.7116	0.6924
0.7083	0.07	800	0.6868	0.7153
0.6882	0.08	1000	0.6638	0.7289
0.6944	0.1	1200	0.6476	0.7361
0.6682	0.11	1400	0.6364	0.7458
0.6635	0.13	1600	0.6592	0.7337
0.6423	0.15	1800	0.6120	0.7510
0.6196	0.16	2000	0.5990	0.7582
0.6381	0.18	2200	0.6026	0.7538
0.6276	0.2	2400	0.6054	0.7598
0.6248	0.21	2600	0.6368	0.7526
0.6331	0.23	2800	0.5959	0.7655
0.6142	0.24	3000	0.6117	0.7554
0.6124	0.26	3200	0.6221	0.7570
0.6127	0.28	3400	0.5748	0.7695
0.602	0.29	3600	0.5735	0.7598
0.5923	0.31	3800	0.5609	0.7723
0.5827	0.33	4000	0.5635	0.7743
0.5732	0.34	4200	0.5547	0.7771
0.5757	0.36	4400	0.5629	0.7739
0.5736	0.37	4600	0.5680	0.7659
0.5642	0.39	4800	0.5437	0.7871
0.5763	0.41	5000	0.5589	0.7807
0.5713	0.42	5200	0.5355	0.7867
0.5644	0.44	5400	0.5346	0.7888
0.5727	0.46	5600	0.5519	0.7815
0.5539	0.47	5800	0.5219	0.7900
0.5516	0.49	6000	0.5560	0.7795
0.5539	0.51	6200	0.5544	0.7847
0.5693	0.52	6400	0.5322	0.7932
0.5632	0.54	6600	0.5404	0.7936
0.565	0.55	6800	0.5382	0.7880
0.5555	0.57	7000	0.5364	0.7920
0.5329	0.59	7200	0.5177	0.7964
0.54	0.6	7400	0.5286	0.7916
0.554	0.62	7600	0.5401	0.7835
0.5447	0.64	7800	0.5261	0.7876
0.5438	0.65	8000	0.5032	0.8020
0.5505	0.67	8200	0.5220	0.7924
0.5364	0.68	8400	0.5398	0.7876
0.5317	0.7	8600	0.5310	0.7944
0.5361	0.72	8800	0.5297	0.7936
0.5204	0.73	9000	0.5270	0.7940
0.5189	0.75	9200	0.5193	0.7964
0.5348	0.77	9400	0.5270	0.7867
0.5363	0.78	9600	0.5194	0.7924
0.5184	0.8	9800	0.5298	0.7888
0.5072	0.81	10000	0.4999	0.7992
0.5229	0.83	10200	0.4922	0.8108
0.5201	0.85	10400	0.5019	0.7920
0.5304	0.86	10600	0.4959	0.7992
0.5061	0.88	10800	0.5047	0.7980
0.5291	0.9	11000	0.4974	0.8068
0.5099	0.91	11200	0.4988	0.8036
0.5271	0.93	11400	0.4899	0.8028
0.5211	0.95	11600	0.4866	0.8092
0.4977	0.96	11800	0.5059	0.7960
0.5155	0.98	12000	0.4821	0.8084
0.5061	0.99	12200	0.4763	0.8116
0.4607	1.01	12400	0.5245	0.8020
0.4435	1.03	12600	0.5021	0.8032
0.4289	1.04	12800	0.5219	0.8060
0.4227	1.06	13000	0.5119	0.8076
0.4349	1.08	13200	0.4957	0.8104
0.4331	1.09	13400	0.4914	0.8129
0.4269	1.11	13600	0.4785	0.8145
0.4185	1.12	13800	0.4879	0.8161
0.4244	1.14	14000	0.4834	0.8149
0.4016	1.16	14200	0.5084	0.8056
0.4106	1.17	14400	0.4993	0.8052
0.4345	1.19	14600	0.5029	0.8124
0.4162	1.21	14800	0.4841	0.8120
0.4239	1.22	15000	0.4756	0.8189
0.4215	1.24	15200	0.4957	0.8088
0.4157	1.25	15400	0.4845	0.8112
0.3982	1.27	15600	0.5064	0.8048
0.4056	1.29	15800	0.4827	0.8241
0.4105	1.3	16000	0.4936	0.8088
0.4221	1.32	16200	0.4800	0.8129
0.4029	1.34	16400	0.4790	0.8181
0.4346	1.35	16600	0.4802	0.8137
0.4163	1.37	16800	0.4838	0.8213
0.4106	1.39	17000	0.4905	0.8209
0.4071	1.4	17200	0.4889	0.8153
0.4077	1.42	17400	0.4801	0.8165
0.4074	1.43	17600	0.4765	0.8217
0.4095	1.45	17800	0.4942	0.8096
0.4117	1.47	18000	0.4668	0.8225
0.3991	1.48	18200	0.4814	0.8161
0.4114	1.5	18400	0.4757	0.8193
0.4061	1.52	18600	0.4702	0.8209
0.4104	1.53	18800	0.4814	0.8149
0.3997	1.55	19000	0.4833	0.8141
0.3992	1.56	19200	0.4847	0.8169
0.4021	1.58	19400	0.4893	0.8189
0.4284	1.6	19600	0.4806	0.8173
0.3915	1.61	19800	0.4952	0.8092
0.4122	1.63	20000	0.4917	0.8112
0.4164	1.65	20200	0.4769	0.8157
0.4063	1.66	20400	0.4723	0.8141
0.4087	1.68	20600	0.4701	0.8157
0.4159	1.69	20800	0.4826	0.8141
0.4	1.71	21000	0.4760	0.8133
0.4024	1.73	21200	0.4755	0.8161
0.4201	1.74	21400	0.4728	0.8173
0.4066	1.76	21600	0.4690	0.8157
0.3941	1.78	21800	0.4687	0.8181
0.3987	1.79	22000	0.4735	0.8149
0.4074	1.81	22200	0.4715	0.8137
0.4083	1.83	22400	0.4660	0.8181
0.4107	1.84	22600	0.4699	0.8161
0.3924	1.86	22800	0.4732	0.8153
0.4205	1.87	23000	0.4686	0.8177
0.3962	1.89	23200	0.4688	0.8177
0.3888	1.91	23400	0.4778	0.8124
0.3978	1.92	23600	0.4713	0.8145
0.3963	1.94	23800	0.4704	0.8145
0.408	1.96	24000	0.4674	0.8165
0.4014	1.97	24200	0.4679	0.8161
0.3951	1.99	24400	0.4681	0.8157

Framework versions

Transformers 4.21.0
Pytorch 1.12.0+cu102
Datasets 2.4.0
Tokenizers 0.12.1

MayaGalvez/bert-base-multilingual-cased-finetuned-nli

bert-base-multilingual-cased-finetuned-nli

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

MayaGalvez/
bert-base-multilingual-cased-finetuned-nli