metadata

license: apache-2.0
base_model: google/flan-t5-small
tags:
  - generated_from_trainer
model-index:
  - name: flant5-tuned-15-warmup
    results: []

flant5-tuned-15-warmup

This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.8983

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:

learning_rate: 0.0005
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 6
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
1.9667	0.02	1	1.6464
2.4545	0.04	2	1.5922
2.3948	0.06	3	1.5379
2.0495	0.09	4	1.4903
1.7473	0.11	5	1.4409
1.5538	0.13	6	1.4121
1.7909	0.15	7	1.3920
1.8065	0.17	8	1.3720
2.0163	0.19	9	1.3446
1.9762	0.21	10	1.3207
1.4572	0.23	11	1.3053
1.8411	0.26	12	1.2928
1.3427	0.28	13	1.2852
1.4388	0.3	14	1.2766
1.738	0.32	15	1.2673
1.4727	0.34	16	1.2620
1.4177	0.36	17	1.2587
1.87	0.38	18	1.2539
1.7525	0.4	19	1.2492
1.6839	0.43	20	1.2478
1.2536	0.45	21	1.2469
1.2651	0.47	22	1.2461
1.3432	0.49	23	1.2433
1.4549	0.51	24	1.2388
1.1316	0.53	25	1.2362
2.1718	0.55	26	1.2301
1.8	0.57	27	1.2234
1.3376	0.6	28	1.2193
1.8136	0.62	29	1.2137
2.0816	0.64	30	1.2099
1.2093	0.66	31	1.2063
1.3496	0.68	32	1.2045
1.5794	0.7	33	1.2028
1.4553	0.72	34	1.2023
1.6841	0.74	35	1.2037
1.3801	0.77	36	1.2072
1.5391	0.79	37	1.2103
1.5746	0.81	38	1.2104
1.4416	0.83	39	1.2095
1.8582	0.85	40	1.2053
1.2527	0.87	41	1.2039
0.9743	0.89	42	1.2062
1.5079	0.91	43	1.2073
1.121	0.94	44	1.2057
1.466	0.96	45	1.2071
1.3134	0.98	46	1.2079
2.7492	1.0	47	1.2056
1.0234	1.02	48	1.2062
0.8741	1.04	49	1.2089
0.9328	1.06	50	1.2153
1.2001	1.09	51	1.2150
1.1934	1.11	52	1.2092
1.4865	1.13	53	1.2003
1.4061	1.15	54	1.1917
0.9929	1.17	55	1.1851
1.3385	1.19	56	1.1796
1.2717	1.21	57	1.1771
0.8547	1.23	58	1.1770
1.0905	1.26	59	1.1771
0.7702	1.28	60	1.1812
1.131	1.3	61	1.1847
1.3995	1.32	62	1.1858
1.2912	1.34	63	1.1859
1.1888	1.36	64	1.1835
1.1689	1.38	65	1.1805
1.3833	1.4	66	1.1770
1.1569	1.43	67	1.1741
1.0094	1.45	68	1.1750
1.411	1.47	69	1.1743
0.9339	1.49	70	1.1760
1.2101	1.51	71	1.1761
1.2961	1.53	72	1.1779
1.0414	1.55	73	1.1818
1.2422	1.57	74	1.1837
0.8604	1.6	75	1.1894
1.2485	1.62	76	1.1947
1.4939	1.64	77	1.1972
1.1532	1.66	78	1.1991
1.3687	1.68	79	1.1996
1.1066	1.7	80	1.1965
1.1804	1.72	81	1.1948
1.0314	1.74	82	1.1939
1.3474	1.77	83	1.1901
1.0698	1.79	84	1.1886
0.9676	1.81	85	1.1897
1.3543	1.83	86	1.1868
1.2849	1.85	87	1.1835
0.6902	1.87	88	1.1868
1.2472	1.89	89	1.1913
1.4595	1.91	90	1.1929
1.052	1.94	91	1.1956
0.7543	1.96	92	1.1987
1.0585	1.98	93	1.2009
0.7874	2.0	94	1.2026
0.9399	2.02	95	1.2039
1.1582	2.04	96	1.2037
0.9806	2.06	97	1.2027
1.1384	2.09	98	1.2063
0.8522	2.11	99	1.2115
1.1167	2.13	100	1.2179
0.7031	2.15	101	1.2275
0.8443	2.17	102	1.2353
0.8372	2.19	103	1.2465
0.8184	2.21	104	1.2573
0.9189	2.23	105	1.2669
0.7656	2.26	106	1.2786
0.9306	2.28	107	1.2826
0.8296	2.3	108	1.2809
0.9204	2.32	109	1.2804
1.0665	2.34	110	1.2780
0.8361	2.36	111	1.2758
0.5151	2.38	112	1.2760
0.9704	2.4	113	1.2757
0.9274	2.43	114	1.2725
0.7455	2.45	115	1.2673
0.7844	2.47	116	1.2660
0.9516	2.49	117	1.2601
0.9778	2.51	118	1.2537
1.1967	2.53	119	1.2446
1.1338	2.55	120	1.2340
0.9777	2.57	121	1.2259
1.0553	2.6	122	1.2203
0.8991	2.62	123	1.2148
0.7514	2.64	124	1.2114
1.0731	2.66	125	1.2096
0.8877	2.68	126	1.2121
0.8157	2.7	127	1.2198
0.7522	2.72	128	1.2328
0.9402	2.74	129	1.2476
1.0729	2.77	130	1.2669
0.6258	2.79	131	1.2889
1.0904	2.81	132	1.3039
1.1231	2.83	133	1.3114
1.1652	2.85	134	1.3144
0.9269	2.87	135	1.3122
1.2235	2.89	136	1.3009
1.1594	2.91	137	1.2821
1.0766	2.94	138	1.2626
1.0211	2.96	139	1.2450
0.7068	2.98	140	1.2319
1.1419	3.0	141	1.2199
0.8477	3.02	142	1.2145
0.7218	3.04	143	1.2107
0.8212	3.06	144	1.2132
0.6607	3.09	145	1.2174
0.8499	3.11	146	1.2231
0.6571	3.13	147	1.2293
0.8632	3.15	148	1.2357
0.7705	3.17	149	1.2440
0.8845	3.19	150	1.2556
0.8118	3.21	151	1.2673
0.8089	3.23	152	1.2785
0.9155	3.26	153	1.2892
0.7645	3.28	154	1.2962
0.8425	3.3	155	1.3024
0.7414	3.32	156	1.3069
0.8212	3.34	157	1.3101
0.6553	3.36	158	1.3102
0.7015	3.38	159	1.3114
0.6462	3.4	160	1.3139
0.8256	3.43	161	1.3137
0.8639	3.45	162	1.3117
0.8675	3.47	163	1.3089
0.7722	3.49	164	1.3049
0.9258	3.51	165	1.3000
0.5696	3.53	166	1.2988
0.6586	3.55	167	1.2959
0.7285	3.57	168	1.2944
0.7846	3.6	169	1.2952
0.8219	3.62	170	1.2961
0.9124	3.64	171	1.2931
0.7936	3.66	172	1.2876
0.8056	3.68	173	1.2840
0.7926	3.7	174	1.2795
0.5121	3.72	175	1.2789
0.7926	3.74	176	1.2803
0.8913	3.77	177	1.2832
0.8464	3.79	178	1.2860
0.79	3.81	179	1.2905
0.5527	3.83	180	1.2957
0.6894	3.85	181	1.3043
0.7436	3.87	182	1.3088
0.5276	3.89	183	1.3112
0.663	3.91	184	1.3112
0.853	3.94	185	1.3071
0.9493	3.96	186	1.2984
0.8933	3.98	187	1.2862
0.6427	4.0	188	1.2739
0.7868	4.02	189	1.2666
0.7293	4.04	190	1.2574
0.6609	4.06	191	1.2506
0.5453	4.09	192	1.2474
0.5715	4.11	193	1.2466
0.6488	4.13	194	1.2479
0.7996	4.15	195	1.2517
0.5844	4.17	196	1.2571
0.4756	4.19	197	1.2665
0.5201	4.21	198	1.2787
0.7375	4.23	199	1.2933
0.6498	4.26	200	1.3068
0.6664	4.28	201	1.3206
0.6631	4.3	202	1.3311
0.5289	4.32	203	1.3396
0.7006	4.34	204	1.3405
0.6375	4.36	205	1.3457
0.5317	4.38	206	1.3534
0.4483	4.4	207	1.3594
0.6698	4.43	208	1.3624
0.5525	4.45	209	1.3630
0.5691	4.47	210	1.3647
0.729	4.49	211	1.3685
0.6684	4.51	212	1.3720
0.8399	4.53	213	1.3716
0.5481	4.55	214	1.3728
0.7812	4.57	215	1.3716
0.7171	4.6	216	1.3670
0.5255	4.62	217	1.3667
0.6313	4.64	218	1.3668
0.6874	4.66	219	1.3626
0.8127	4.68	220	1.3584
0.9066	4.7	221	1.3530
0.6459	4.72	222	1.3505
0.7397	4.74	223	1.3487
0.682	4.77	224	1.3489
0.68	4.79	225	1.3500
0.6817	4.81	226	1.3498
0.6286	4.83	227	1.3461
0.5497	4.85	228	1.3435
0.6971	4.87	229	1.3378
0.6783	4.89	230	1.3324
0.6756	4.91	231	1.3300
0.6324	4.94	232	1.3269
0.8509	4.96	233	1.3221
0.6038	4.98	234	1.3205
0.553	5.0	235	1.3215
0.578	5.02	236	1.3245
0.5989	5.04	237	1.3290
0.5484	5.06	238	1.3323
0.6911	5.09	239	1.3344
0.5842	5.11	240	1.3378
0.626	5.13	241	1.3392
0.5394	5.15	242	1.3404
0.414	5.17	243	1.3422
0.5411	5.19	244	1.3460
0.5132	5.21	245	1.3515
0.6066	5.23	246	1.3541
0.4444	5.26	247	1.3565
0.6967	5.28	248	1.3586
0.4968	5.3	249	1.3616
0.4654	5.32	250	1.3675
0.4641	5.34	251	1.3737
0.6655	5.36	252	1.3783
0.5444	5.38	253	1.3859
0.4906	5.4	254	1.3902
0.3241	5.43	255	1.3976
0.6621	5.45	256	1.4057
0.5488	5.47	257	1.4133
0.4694	5.49	258	1.4230
0.4817	5.51	259	1.4322
0.4688	5.53	260	1.4411
0.6659	5.55	261	1.4454
0.5845	5.57	262	1.4499
0.7268	5.6	263	1.4523
0.5856	5.62	264	1.4559
0.6117	5.64	265	1.4602
0.3784	5.66	266	1.4646
0.4126	5.68	267	1.4721
0.4252	5.7	268	1.4776
0.6552	5.72	269	1.4837
0.4844	5.74	270	1.4882
0.5981	5.77	271	1.4871
0.4637	5.79	272	1.4882
0.5158	5.81	273	1.4879
0.5121	5.83	274	1.4851
0.6141	5.85	275	1.4785
0.4286	5.87	276	1.4694
0.5169	5.89	277	1.4594
0.4068	5.91	278	1.4465
0.7558	5.94	279	1.4321
0.577	5.96	280	1.4198
0.4013	5.98	281	1.4108
0.4206	6.0	282	1.4061
0.4977	6.02	283	1.4048
0.2022	6.04	284	1.4073
0.4111	6.06	285	1.4093
0.515	6.09	286	1.4133
0.4454	6.11	287	1.4179
0.5122	6.13	288	1.4260
0.4325	6.15	289	1.4345
0.4148	6.17	290	1.4449
0.4545	6.19	291	1.4530
0.5699	6.21	292	1.4571
0.4644	6.23	293	1.4598
0.2725	6.26	294	1.4624
0.5681	6.28	295	1.4651
0.3317	6.3	296	1.4690
0.4195	6.32	297	1.4742
0.3594	6.34	298	1.4825
0.4206	6.36	299	1.4851
0.439	6.38	300	1.4881
0.5487	6.4	301	1.4914
0.4921	6.43	302	1.4944
0.5617	6.45	303	1.4955
0.4626	6.47	304	1.4965
0.279	6.49	305	1.5023
0.2747	6.51	306	1.5111
0.4798	6.53	307	1.5211
0.4571	6.55	308	1.5314
0.5165	6.57	309	1.5416
0.5369	6.6	310	1.5524
0.3594	6.62	311	1.5630
0.4679	6.64	312	1.5735
0.5307	6.66	313	1.5794
0.3433	6.68	314	1.5790
0.5281	6.7	315	1.5700
0.5548	6.72	316	1.5574
0.4698	6.74	317	1.5480
0.4761	6.77	318	1.5428
0.4868	6.79	319	1.5359
0.4529	6.81	320	1.5291
0.4167	6.83	321	1.5213
0.3737	6.85	322	1.5193
0.4094	6.87	323	1.5173
0.5852	6.89	324	1.5117
0.5481	6.91	325	1.5043
0.6539	6.94	326	1.4967
0.3777	6.96	327	1.4886
0.8028	6.98	328	1.4796
0.4962	7.0	329	1.4724
0.3474	7.02	330	1.4738
0.3377	7.04	331	1.4769
0.4103	7.06	332	1.4824
0.3783	7.09	333	1.4918
0.36	7.11	334	1.5018
0.4372	7.13	335	1.5099
0.392	7.15	336	1.5195
0.5038	7.17	337	1.5278
0.3428	7.19	338	1.5334
0.4336	7.21	339	1.5388
0.3686	7.23	340	1.5470
0.4996	7.26	341	1.5559
0.3488	7.28	342	1.5633
0.431	7.3	343	1.5704
0.4227	7.32	344	1.5771
0.4292	7.34	345	1.5838
0.3743	7.36	346	1.5902
0.4733	7.38	347	1.5941
0.3452	7.4	348	1.5967
0.4762	7.43	349	1.5962
0.5231	7.45	350	1.5935
0.3525	7.47	351	1.5889
0.3958	7.49	352	1.5846
0.4228	7.51	353	1.5752
0.3241	7.53	354	1.5636
0.4223	7.55	355	1.5523
0.3235	7.57	356	1.5422
0.367	7.6	357	1.5332
0.3111	7.62	358	1.5241
0.4455	7.64	359	1.5191
0.5601	7.66	360	1.5117
0.4029	7.68	361	1.5044
0.3047	7.7	362	1.4992
0.3186	7.72	363	1.4957
0.4467	7.74	364	1.4933
0.241	7.77	365	1.4911
0.4157	7.79	366	1.4893
0.4411	7.81	367	1.4903
0.2902	7.83	368	1.4948
0.4178	7.85	369	1.5007
0.4681	7.87	370	1.5046
0.4625	7.89	371	1.5078
0.4616	7.91	372	1.5120
0.4523	7.94	373	1.5196
0.3865	7.96	374	1.5284
0.4603	7.98	375	1.5367
0.57	8.0	376	1.5452
0.5478	8.02	377	1.5552
0.3629	8.04	378	1.5683
0.5328	8.06	379	1.5783
0.2767	8.09	380	1.5865
0.2588	8.11	381	1.5995
0.3669	8.13	382	1.6075
0.3093	8.15	383	1.6151
0.3499	8.17	384	1.6184
0.2385	8.19	385	1.6236
0.2133	8.21	386	1.6282
0.5247	8.23	387	1.6299
0.2788	8.26	388	1.6301
0.2888	8.28	389	1.6310
0.2901	8.3	390	1.6311
0.2557	8.32	391	1.6334
0.3429	8.34	392	1.6341
0.2947	8.36	393	1.6360
0.3409	8.38	394	1.6378
0.5129	8.4	395	1.6381
0.3732	8.43	396	1.6397
0.2853	8.45	397	1.6403
0.3009	8.47	398	1.6437
0.3477	8.49	399	1.6464
0.3348	8.51	400	1.6465
0.304	8.53	401	1.6459
0.3394	8.55	402	1.6463
0.2765	8.57	403	1.6462
0.4465	8.6	404	1.6463
0.1313	8.62	405	1.6502
0.3853	8.64	406	1.6536
0.4603	8.66	407	1.6536
0.3012	8.68	408	1.6541
0.3678	8.7	409	1.6567
0.2448	8.72	410	1.6597
0.3505	8.74	411	1.6611
0.3566	8.77	412	1.6631
0.3387	8.79	413	1.6672
0.2605	8.81	414	1.6724
0.356	8.83	415	1.6746
0.3888	8.85	416	1.6749
0.2549	8.87	417	1.6734
0.4423	8.89	418	1.6725
0.3891	8.91	419	1.6715
0.265	8.94	420	1.6739
0.2408	8.96	421	1.6741
0.3052	8.98	422	1.6764
0.4059	9.0	423	1.6759
0.1609	9.02	424	1.6761
0.3744	9.04	425	1.6728
0.314	9.06	426	1.6685
0.2212	9.09	427	1.6662
0.3075	9.11	428	1.6659
0.2805	9.13	429	1.6673
0.3546	9.15	430	1.6701
0.3561	9.17	431	1.6746
0.267	9.19	432	1.6792
0.2871	9.21	433	1.6842
0.3459	9.23	434	1.6876
0.2278	9.26	435	1.6907
0.3941	9.28	436	1.6912
0.3931	9.3	437	1.6916
0.402	9.32	438	1.6928
0.2264	9.34	439	1.6952
0.2447	9.36	440	1.6968
0.1912	9.38	441	1.6985
0.158	9.4	442	1.7016
0.3027	9.43	443	1.7041
0.346	9.45	444	1.7073
0.2865	9.47	445	1.7128
0.3778	9.49	446	1.7169
0.2313	9.51	447	1.7218
0.2888	9.53	448	1.7265
0.3416	9.55	449	1.7326
0.1626	9.57	450	1.7391
0.2913	9.6	451	1.7448
0.3407	9.62	452	1.7458
0.3941	9.64	453	1.7445
0.3097	9.66	454	1.7409
0.3994	9.68	455	1.7356
0.3246	9.7	456	1.7290
0.2785	9.72	457	1.7227
0.4201	9.74	458	1.7139
0.4037	9.77	459	1.7047
0.2456	9.79	460	1.6972
0.212	9.81	461	1.6931
0.1711	9.83	462	1.6907
0.2962	9.85	463	1.6900
0.3199	9.87	464	1.6910
0.2904	9.89	465	1.6936
0.302	9.91	466	1.6970
0.3182	9.94	467	1.6990
0.2295	9.96	468	1.7035
0.3589	9.98	469	1.7093
0.3064	10.0	470	1.7129
0.2836	10.02	471	1.7177
0.3143	10.04	472	1.7212
0.3142	10.06	473	1.7258
0.2692	10.09	474	1.7309
0.2338	10.11	475	1.7352
0.3044	10.13	476	1.7431
0.2134	10.15	477	1.7535
0.2768	10.17	478	1.7632
0.2931	10.19	479	1.7712
0.2469	10.21	480	1.7789
0.2124	10.23	481	1.7828
0.2593	10.26	482	1.7841
0.2401	10.28	483	1.7846
0.2539	10.3	484	1.7848
0.377	10.32	485	1.7821
0.2868	10.34	486	1.7788
0.2668	10.36	487	1.7750
0.3051	10.38	488	1.7711
0.2884	10.4	489	1.7675
0.19	10.43	490	1.7645
0.2492	10.45	491	1.7629
0.1944	10.47	492	1.7621
0.1992	10.49	493	1.7635
0.2735	10.51	494	1.7656
0.2468	10.53	495	1.7698
0.4186	10.55	496	1.7738
0.1926	10.57	497	1.7778
0.2059	10.6	498	1.7801
0.2694	10.62	499	1.7808
0.2372	10.64	500	1.7820
0.4205	10.66	501	1.7803
0.3153	10.68	502	1.7782
0.2384	10.7	503	1.7755
0.1864	10.72	504	1.7724
0.2341	10.74	505	1.7716
0.1731	10.77	506	1.7730
0.3016	10.79	507	1.7717
0.2975	10.81	508	1.7684
0.1668	10.83	509	1.7665
0.2462	10.85	510	1.7663
0.2779	10.87	511	1.7652
0.1888	10.89	512	1.7648
0.1881	10.91	513	1.7668
0.3798	10.94	514	1.7690
0.326	10.96	515	1.7708
0.2523	10.98	516	1.7704
0.2867	11.0	517	1.7693
0.2152	11.02	518	1.7700
0.1946	11.04	519	1.7725
0.2697	11.06	520	1.7753
0.1924	11.09	521	1.7768
0.2121	11.11	522	1.7797
0.2806	11.13	523	1.7823
0.1763	11.15	524	1.7851
0.2627	11.17	525	1.7882
0.2913	11.19	526	1.7906
0.3136	11.21	527	1.7934
0.228	11.23	528	1.7978
0.228	11.26	529	1.8011
0.2112	11.28	530	1.8043
0.2009	11.3	531	1.8086
0.3176	11.32	532	1.8107
0.2518	11.34	533	1.8109
0.3709	11.36	534	1.8092
0.3511	11.38	535	1.8068
0.273	11.4	536	1.8046
0.3282	11.43	537	1.8027
0.2163	11.45	538	1.8010
0.2399	11.47	539	1.7990
0.2226	11.49	540	1.7994
0.2135	11.51	541	1.8000
0.296	11.53	542	1.7996
0.2127	11.55	543	1.7988
0.1766	11.57	544	1.7986
0.3086	11.6	545	1.7980
0.1889	11.62	546	1.7981
0.2833	11.64	547	1.7980
0.2744	11.66	548	1.7972
0.3597	11.68	549	1.7969
0.2974	11.7	550	1.7961
0.289	11.72	551	1.7951
0.1491	11.74	552	1.7953
0.2238	11.77	553	1.7948
0.1382	11.79	554	1.7939
0.1744	11.81	555	1.7902
0.2266	11.83	556	1.7867
0.2311	11.85	557	1.7837
0.2088	11.87	558	1.7814
0.2171	11.89	559	1.7803
0.1469	11.91	560	1.7798
0.1879	11.94	561	1.7804
0.1839	11.96	562	1.7802
0.3219	11.98	563	1.7801
0.1393	12.0	564	1.7815
0.2543	12.02	565	1.7813
0.2255	12.04	566	1.7807
0.3332	12.06	567	1.7795
0.2031	12.09	568	1.7781
0.2543	12.11	569	1.7764
0.14	12.13	570	1.7760
0.1849	12.15	571	1.7745
0.3535	12.17	572	1.7734
0.2025	12.19	573	1.7732
0.2843	12.21	574	1.7734
0.2304	12.23	575	1.7742
0.2265	12.26	576	1.7756
0.2131	12.28	577	1.7769
0.1659	12.3	578	1.7785
0.1337	12.32	579	1.7804
0.1894	12.34	580	1.7826
0.2161	12.36	581	1.7856
0.1821	12.38	582	1.7884
0.2542	12.4	583	1.7918
0.2338	12.43	584	1.7953
0.2506	12.45	585	1.7993
0.0851	12.47	586	1.8036
0.1985	12.49	587	1.8086
0.2765	12.51	588	1.8123
0.1759	12.53	589	1.8157
0.1825	12.55	590	1.8198
0.1824	12.57	591	1.8224
0.2272	12.6	592	1.8253
0.2015	12.62	593	1.8273
0.2074	12.64	594	1.8291
0.2824	12.66	595	1.8316
0.2268	12.68	596	1.8339
0.3189	12.7	597	1.8370
0.251	12.72	598	1.8416
0.2135	12.74	599	1.8455
0.2548	12.77	600	1.8493
0.2579	12.79	601	1.8519
0.09	12.81	602	1.8546
0.2147	12.83	603	1.8567
0.239	12.85	604	1.8584
0.1586	12.87	605	1.8608
0.252	12.89	606	1.8637
0.2653	12.91	607	1.8658
0.1741	12.94	608	1.8675
0.2943	12.96	609	1.8684
0.2498	12.98	610	1.8694
0.2415	13.0	611	1.8696
0.1688	13.02	612	1.8699
0.182	13.04	613	1.8707
0.203	13.06	614	1.8714
0.1876	13.09	615	1.8717
0.1892	13.11	616	1.8718
0.2952	13.13	617	1.8709
0.1553	13.15	618	1.8703
0.1796	13.17	619	1.8700
0.2248	13.19	620	1.8701
0.2618	13.21	621	1.8703
0.312	13.23	622	1.8701
0.1238	13.26	623	1.8710
0.2009	13.28	624	1.8717
0.1822	13.3	625	1.8724
0.1444	13.32	626	1.8728
0.1802	13.34	627	1.8737
0.1095	13.36	628	1.8749
0.1677	13.38	629	1.8758
0.181	13.4	630	1.8771
0.1816	13.43	631	1.8780
0.1952	13.45	632	1.8796
0.197	13.47	633	1.8809
0.2085	13.49	634	1.8827
0.193	13.51	635	1.8843
0.297	13.53	636	1.8852
0.2068	13.55	637	1.8857
0.1825	13.57	638	1.8857
0.3174	13.6	639	1.8850
0.2319	13.62	640	1.8849
0.2063	13.64	641	1.8848
0.228	13.66	642	1.8850
0.268	13.68	643	1.8846
0.2585	13.7	644	1.8843
0.1712	13.72	645	1.8848
0.2408	13.74	646	1.8852
0.1786	13.77	647	1.8861
0.1343	13.79	648	1.8869
0.2155	13.81	649	1.8874
0.2248	13.83	650	1.8880
0.2193	13.85	651	1.8884
0.2564	13.87	652	1.8889
0.218	13.89	653	1.8892
0.1315	13.91	654	1.8899
0.1327	13.94	655	1.8902
0.1819	13.96	656	1.8901
0.2307	13.98	657	1.8901
0.1718	14.0	658	1.8902
0.2024	14.02	659	1.8899
0.2211	14.04	660	1.8894
0.1243	14.06	661	1.8893
0.35	14.09	662	1.8890
0.2275	14.11	663	1.8888
0.1209	14.13	664	1.8886
0.2861	14.15	665	1.8881
0.1925	14.17	666	1.8880
0.2182	14.19	667	1.8875
0.2353	14.21	668	1.8873
0.305	14.23	669	1.8869
0.1312	14.26	670	1.8868
0.139	14.28	671	1.8867
0.1758	14.3	672	1.8869
0.2613	14.32	673	1.8873
0.2221	14.34	674	1.8878
0.1455	14.36	675	1.8883
0.1665	14.38	676	1.8889
0.1638	14.4	677	1.8895
0.2852	14.43	678	1.8897
0.2016	14.45	679	1.8897
0.1359	14.47	680	1.8903
0.2311	14.49	681	1.8909
0.1748	14.51	682	1.8915
0.2165	14.53	683	1.8923
0.1742	14.55	684	1.8929
0.2248	14.57	685	1.8934
0.2172	14.6	686	1.8940
0.2609	14.62	687	1.8944
0.1902	14.64	688	1.8949
0.1513	14.66	689	1.8954
0.1459	14.68	690	1.8959
0.1359	14.7	691	1.8964
0.1917	14.72	692	1.8968
0.1297	14.74	693	1.8973
0.2252	14.77	694	1.8976
0.2546	14.79	695	1.8979
0.1937	14.81	696	1.8981
0.1236	14.83	697	1.8983
0.1914	14.85	698	1.8983
0.2744	14.87	699	1.8984
0.1895	14.89	700	1.8984
0.151	14.91	701	1.8983
0.1989	14.94	702	1.8983
0.2606	14.96	703	1.8983
0.2467	14.98	704	1.8983
0.2599	15.0	705	1.8983

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2