mistral7b-prot_drug_v3

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.8262

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: 5e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 150
• training_steps: 10000

Training results

Training Loss	Epoch	Step	Validation Loss
12.2364	0.001	10	12.2580
12.2538	0.002	20	12.2579
12.2055	0.003	30	12.1440
11.6943	0.004	40	11.6417
10.6452	0.005	50	10.5062
9.8223	0.006	60	9.7715
9.4474	0.007	70	9.3852
9.1453	0.008	80	9.1029
8.9615	0.009	90	8.9474
8.8465	0.01	100	8.8406
8.7879	0.011	110	8.7700
8.7827	0.012	120	8.7186
8.6959	0.013	130	8.6640
8.6054	0.014	140	8.6110
8.5561	0.015	150	8.5594
8.5363	0.016	160	8.5088
8.4524	0.017	170	8.4677
8.4272	0.018	180	8.4286
8.4157	0.019	190	8.3923
8.3718	0.02	200	8.3564
8.378	0.021	210	8.3324
8.2871	0.022	220	8.3087
8.2918	0.023	230	8.2867
8.2612	0.024	240	8.2691
8.2566	0.025	250	8.2496
8.244	0.026	260	8.2343
8.2375	0.027	270	8.2196
8.2281	0.028	280	8.2038
8.1959	0.029	290	8.1880
8.1431	0.03	300	8.1741
8.1935	0.031	310	8.1616
8.1176	0.032	320	8.1498
8.1305	0.033	330	8.1371
8.1629	0.034	340	8.1234
8.1547	0.035	350	8.1136
8.1045	0.036	360	8.0993
8.0428	0.037	370	8.0869
8.0725	0.038	380	8.0743
8.1115	0.039	390	8.0618
8.0546	0.04	400	8.0459
8.0069	0.041	410	8.0330
8.0262	0.042	420	8.0187
8.0163	0.043	430	8.0051
8.033	0.044	440	7.9856
7.9801	0.045	450	7.9659
8.0104	0.046	460	7.9476
7.9065	0.047	470	7.9328
7.9391	0.048	480	7.9146
7.9332	0.049	490	7.8955
7.9022	0.05	500	7.8777
7.9582	0.051	510	7.8616
7.796	0.052	520	7.8458
7.8622	0.053	530	7.8395
7.7842	0.054	540	7.8322
7.7378	0.055	550	7.8200
7.8312	0.056	560	7.7969
7.7772	0.057	570	7.7759
7.7291	0.058	580	7.7632
7.6453	0.059	590	7.7421
7.7074	0.06	600	7.7219
7.7426	0.061	610	7.7082
7.7015	0.062	620	7.6867
7.7255	0.063	630	7.6894
7.5727	0.064	640	7.6845
7.5956	0.065	650	7.6511
7.6682	0.066	660	7.6424
7.6006	0.067	670	7.6298
7.5442	0.068	680	7.6068
7.4813	0.069	690	7.5913
7.5443	0.07	700	7.5727
7.4999	0.071	710	7.5776
7.4107	0.072	720	7.5509
7.2988	0.073	730	7.5337
7.4865	0.074	740	7.5346
7.3154	0.075	750	7.5266
7.3384	0.076	760	7.5374
7.3143	0.077	770	7.4840
7.2809	0.078	780	7.4725
7.4503	0.079	790	7.4531
7.4023	0.08	800	7.4552
7.3706	0.081	810	7.4295
7.2162	0.082	820	7.4149
7.3256	0.083	830	7.4004
7.2159	0.084	840	7.3929
7.2994	0.085	850	7.3833
7.2248	0.086	860	7.3756
7.1024	0.087	870	7.3452
6.998	0.088	880	7.3480
7.1061	0.089	890	7.3221
7.0424	0.09	900	7.3194
6.9365	0.091	910	7.3024
7.2529	0.092	920	7.2871
7.0291	0.093	930	7.2664
7.0028	0.094	940	7.2584
7.0356	0.095	950	7.2406
7.2134	0.096	960	7.2339
6.9633	0.097	970	7.2348
6.9787	0.098	980	7.2054
6.8275	0.099	990	7.2243
6.7732	0.1	1000	7.1846
6.8486	0.101	1010	7.1695
6.9993	0.102	1020	7.1584
6.8375	0.103	1030	7.1449
6.9323	0.104	1040	7.1625
6.6631	0.105	1050	7.1204
6.8773	0.106	1060	7.1152
6.7742	0.107	1070	7.0885
6.6346	0.108	1080	7.0931
6.8887	0.109	1090	7.0688
6.6428	0.11	1100	7.0510
6.7303	0.111	1110	7.0427
6.6575	0.112	1120	7.0429
6.7771	0.113	1130	7.0457
6.8116	0.114	1140	7.0086
6.5378	0.115	1150	6.9987
6.5589	0.116	1160	6.9816
6.7171	0.117	1170	6.9716
6.7946	0.118	1180	6.9628
6.5923	0.119	1190	6.9751
6.586	0.12	1200	6.9526
6.5764	0.121	1210	6.9108
6.6872	0.122	1220	6.9042
6.624	0.123	1230	6.8768
6.5932	0.124	1240	6.8674
6.5751	0.125	1250	6.8498
6.5996	0.126	1260	6.8611
6.4514	0.127	1270	6.8212
6.3967	0.128	1280	6.8187
6.5969	0.129	1290	6.7885
6.2129	0.13	1300	6.7825
6.3972	0.131	1310	6.7691
6.2758	0.132	1320	6.7835
6.3034	0.133	1330	6.7440
6.223	0.134	1340	6.7446
6.1803	0.135	1350	6.7228
6.1901	0.136	1360	6.7312
6.1488	0.137	1370	6.7461
6.4268	0.138	1380	6.6944
6.1097	0.139	1390	6.6996
6.2065	0.14	1400	6.6577
6.1712	0.141	1410	6.6695
6.2496	0.142	1420	6.6388
6.0074	0.143	1430	6.6316
6.0693	0.144	1440	6.6413
6.2797	0.145	1450	6.6134
6.1959	0.146	1460	6.5926
5.688	0.147	1470	6.6092
5.9011	0.148	1480	6.5788
6.0966	0.149	1490	6.5760
5.988	0.15	1500	6.5549
5.9875	0.151	1510	6.5311
6.2712	0.152	1520	6.5395
5.876	0.153	1530	6.4933
6.2395	0.154	1540	6.4818
6.1336	0.155	1550	6.4639
6.0093	0.156	1560	6.4503
5.7843	0.157	1570	6.4412
5.8853	0.158	1580	6.4297
5.7267	0.159	1590	6.4310
5.6362	0.16	1600	6.4207
5.7044	0.161	1610	6.3831
5.5665	0.162	1620	6.4134
5.8903	0.163	1630	6.3434
5.7121	0.164	1640	6.3576
5.8969	0.165	1650	6.3181
5.4254	0.166	1660	6.3523
5.9054	0.167	1670	6.2956
5.5509	0.168	1680	6.2967
5.8448	0.169	1690	6.2745
5.5366	0.17	1700	6.2954
5.4746	0.171	1710	6.2462
5.5834	0.172	1720	6.2781
5.3858	0.173	1730	6.2220
5.4884	0.174	1740	6.2547
5.2019	0.175	1750	6.2042
5.5335	0.176	1760	6.2185
5.3422	0.177	1770	6.1912
5.0847	0.178	1780	6.2377
5.2894	0.179	1790	6.1815
5.6486	0.18	1800	6.1853
5.7692	0.181	1810	6.1511
5.5303	0.182	1820	6.1688
5.7258	0.183	1830	6.1253
5.4578	0.184	1840	6.1357
5.3214	0.185	1850	6.1000
5.5131	0.186	1860	6.1270
5.2041	0.187	1870	6.0746
5.5318	0.188	1880	6.0855
5.428	0.189	1890	6.0538
5.4626	0.19	1900	6.0807
5.3244	0.191	1910	6.0371
5.436	0.192	1920	6.0449
5.1186	0.193	1930	6.0294
5.2579	0.194	1940	6.0199
5.3326	0.195	1950	6.0073
5.1449	0.196	1960	6.0001
4.9562	0.197	1970	5.9792
5.5297	0.198	1980	6.0049
4.9444	0.199	1990	5.9524
5.1068	0.2	2000	5.9512
5.0556	0.201	2010	5.9322
5.1993	0.202	2020	5.9269
5.3429	0.203	2030	5.9028
5.2428	0.204	2040	5.9443
4.9172	0.205	2050	5.8660
5.1998	0.206	2060	5.8664
4.9477	0.207	2070	5.8598
4.8198	0.208	2080	5.8836
4.7644	0.209	2090	5.8335
5.2563	0.21	2100	5.8696
4.9652	0.211	2110	5.8438
4.9926	0.212	2120	5.8169
5.1937	0.213	2130	5.8058
4.891	0.214	2140	5.8541
5.0321	0.215	2150	5.7719
4.7933	0.216	2160	5.8087
4.7404	0.217	2170	5.7441
4.9161	0.218	2180	5.7692
4.7018	0.219	2190	5.7192
4.9765	0.22	2200	5.7200
4.751	0.221	2210	5.7267
4.9347	0.222	2220	5.7534
4.7404	0.223	2230	5.6849
4.6081	0.224	2240	5.7117
4.5994	0.225	2250	5.6686
4.5841	0.226	2260	5.6593
4.7333	0.227	2270	5.6718
4.347	0.228	2280	5.6530
4.5628	0.229	2290	5.6396
4.6724	0.23	2300	5.6319
4.5283	0.231	2310	5.6177
4.4413	0.232	2320	5.6090
4.8927	0.233	2330	5.5939
4.5664	0.234	2340	5.5713
4.8895	0.235	2350	5.5731
4.3864	0.236	2360	5.5706
4.1588	0.237	2370	5.5435
4.5261	0.238	2380	5.5286
4.7396	0.239	2390	5.5223
4.4675	0.24	2400	5.5216
4.4094	0.241	2410	5.5106
4.5677	0.242	2420	5.5040
4.5906	0.243	2430	5.5018
4.4687	0.244	2440	5.4824
4.7256	0.245	2450	5.4582
4.9141	0.246	2460	5.4740
4.6816	0.247	2470	5.4350
4.5466	0.248	2480	5.4337
4.3248	0.249	2490	5.4114
4.2467	0.25	2500	5.4026
4.45	0.251	2510	5.4229
4.2385	0.252	2520	5.4195
4.7523	0.253	2530	5.3775
4.393	0.254	2540	5.4080
4.3729	0.255	2550	5.3599
4.2651	0.256	2560	5.3542
4.3062	0.257	2570	5.3573
4.144	0.258	2580	5.3535
4.1154	0.259	2590	5.3360
4.2803	0.26	2600	5.3064
4.0842	0.261	2610	5.2963
4.5961	0.262	2620	5.2787
4.206	0.263	2630	5.3152
4.0113	0.264	2640	5.2645
4.1818	0.265	2650	5.2886
3.9046	0.266	2660	5.2585
4.2402	0.267	2670	5.2670
3.8925	0.268	2680	5.2376
4.1357	0.269	2690	5.2307
4.0433	0.27	2700	5.2219
4.009	0.271	2710	5.2389
3.8507	0.272	2720	5.2104
3.8764	0.273	2730	5.2488
3.9827	0.274	2740	5.2257
3.8345	0.275	2750	5.2038
3.903	0.276	2760	5.2007
3.9838	0.277	2770	5.1793
3.9834	0.278	2780	5.1764
3.9531	0.279	2790	5.1368
3.806	0.28	2800	5.1289
3.966	0.281	2810	5.1233
3.8111	0.282	2820	5.1194
3.7297	0.283	2830	5.1063
3.6966	0.284	2840	5.1248
4.0592	0.285	2850	5.0666
3.4351	0.286	2860	5.1165
3.8662	0.287	2870	5.0603
3.8637	0.288	2880	5.0894
3.5666	0.289	2890	5.0620
3.4218	0.29	2900	5.0595
3.5184	0.291	2910	5.0326
3.793	0.292	2920	5.0317
3.6773	0.293	2930	5.0399
3.7499	0.294	2940	5.0159
3.2161	0.295	2950	5.0333
3.844	0.296	2960	5.0068
3.6509	0.297	2970	5.0012
3.6658	0.298	2980	4.9962
3.5109	0.299	2990	4.9917
3.7466	0.3	3000	4.9831
3.6994	0.301	3010	4.9641
3.5568	0.302	3020	4.9757
3.4801	0.303	3030	4.9694
3.4071	0.304	3040	4.9631
3.6507	0.305	3050	4.9496
3.827	0.306	3060	4.9543
3.5014	0.307	3070	4.9562
3.882	0.308	3080	4.9346
3.6937	0.309	3090	4.9244
3.6413	0.31	3100	4.9023
3.5366	0.311	3110	4.8983
3.682	0.312	3120	4.9122
3.477	0.313	3130	4.8850
3.436	0.314	3140	4.8897
3.5179	0.315	3150	4.8502
3.757	0.316	3160	4.8610
3.3943	0.317	3170	4.8700
3.594	0.318	3180	4.8469
3.3679	0.319	3190	4.8410
3.2852	0.32	3200	4.8403
3.5099	0.321	3210	4.8284
3.2652	0.322	3220	4.8076
3.2544	0.323	3230	4.8024
3.5837	0.324	3240	4.8087
3.3361	0.325	3250	4.7988
3.7445	0.326	3260	4.7793
3.1541	0.327	3270	4.7758
3.4536	0.328	3280	4.7704
3.0832	0.329	3290	4.7707
3.016	0.33	3300	4.7831
3.4494	0.331	3310	4.7691
3.3187	0.332	3320	4.7387
3.3214	0.333	3330	4.7462
3.3581	0.334	3340	4.7231
3.0002	0.335	3350	4.7499
3.3687	0.336	3360	4.7470
3.094	0.337	3370	4.7484
3.3225	0.338	3380	4.7429
3.4161	0.339	3390	4.7351
3.4943	0.34	3400	4.7377
3.2304	0.341	3410	4.6883
3.2658	0.342	3420	4.6949
3.2962	0.343	3430	4.6828
3.1118	0.344	3440	4.7356
3.2952	0.345	3450	4.6515
3.1971	0.346	3460	4.6993
3.1475	0.347	3470	4.6365
2.9313	0.348	3480	4.6547
3.0061	0.349	3490	4.6716
3.1617	0.35	3500	4.6556
3.1452	0.351	3510	4.6804
3.031	0.352	3520	4.6432
2.8135	0.353	3530	4.6276
3.0721	0.354	3540	4.6370
2.8183	0.355	3550	4.6271
3.0968	0.356	3560	4.6137
2.8955	0.357	3570	4.6244
2.9859	0.358	3580	4.6232
3.1059	0.359	3590	4.5983
2.9247	0.36	3600	4.6214
3.1088	0.361	3610	4.6124
2.9014	0.362	3620	4.5827
2.6364	0.363	3630	4.5949
2.5239	0.364	3640	4.5933
2.6432	0.365	3650	4.6005
2.8269	0.366	3660	4.5834
3.0858	0.367	3670	4.5556
2.9176	0.368	3680	4.5939
2.6451	0.369	3690	4.5774
2.8993	0.37	3700	4.5794
3.001	0.371	3710	4.5771
2.8974	0.372	3720	4.5481
3.1128	0.373	3730	4.5360
3.1101	0.374	3740	4.5210
2.925	0.375	3750	4.5232
2.7071	0.376	3760	4.5120
2.909	0.377	3770	4.5186
3.1354	0.378	3780	4.5167
2.9686	0.379	3790	4.5036
2.8366	0.38	3800	4.4991
2.8439	0.381	3810	4.4882
2.7405	0.382	3820	4.5092
2.8334	0.383	3830	4.5080
2.8425	0.384	3840	4.4927
2.8276	0.385	3850	4.4669
2.8562	0.386	3860	4.4709
2.714	0.387	3870	4.4791
2.5857	0.388	3880	4.4823
3.0127	0.389	3890	4.4737
2.9474	0.39	3900	4.4635
2.6787	0.391	3910	4.4818
2.5056	0.392	3920	4.4891
2.6681	0.393	3930	4.4466
2.731	0.394	3940	4.4348
2.6296	0.395	3950	4.4535
2.4331	0.396	3960	4.4111
2.6591	0.397	3970	4.4131
2.5106	0.398	3980	4.4291
2.4048	0.399	3990	4.4289
2.6684	0.4	4000	4.4355
2.5881	0.401	4010	4.4045
2.6618	0.402	4020	4.4015
2.8528	0.403	4030	4.3969
2.6552	0.404	4040	4.3884
2.7652	0.405	4050	4.3736
2.5634	0.406	4060	4.3906
2.7591	0.407	4070	4.3789
2.565	0.408	4080	4.4054
2.7409	0.409	4090	4.3558
2.6925	0.41	4100	4.3551
2.4577	0.411	4110	4.3784
2.5328	0.412	4120	4.3705
2.4659	0.413	4130	4.3607
2.3694	0.414	4140	4.3782
2.2693	0.415	4150	4.3734
2.6328	0.416	4160	4.3415
2.3923	0.417	4170	4.3617
2.7774	0.418	4180	4.3233
2.5612	0.419	4190	4.3398
2.6467	0.42	4200	4.3341
2.5213	0.421	4210	4.3545
2.5671	0.422	4220	4.3349
2.5758	0.423	4230	4.3337
2.3845	0.424	4240	4.3000
2.4242	0.425	4250	4.3203
2.2893	0.426	4260	4.3325
2.4254	0.427	4270	4.3320
2.2907	0.428	4280	4.3187
2.3777	0.429	4290	4.2932
2.4253	0.43	4300	4.3142
2.3261	0.431	4310	4.3024
2.4036	0.432	4320	4.2992
2.5113	0.433	4330	4.3141
2.3572	0.434	4340	4.2848
2.3879	0.435	4350	4.2834
2.3793	0.436	4360	4.2627
2.4736	0.437	4370	4.2595
2.5159	0.438	4380	4.2835
2.3629	0.439	4390	4.2863
2.1938	0.44	4400	4.2670
2.3449	0.441	4410	4.2716
2.3991	0.442	4420	4.2669
2.4827	0.443	4430	4.2406
2.3855	0.444	4440	4.2715
2.1299	0.445	4450	4.2495
2.0333	0.446	4460	4.2827
1.9878	0.447	4470	4.2827
2.3024	0.448	4480	4.2609
2.4138	0.449	4490	4.2310
2.2039	0.45	4500	4.2546
2.3207	0.451	4510	4.2290
2.4231	0.452	4520	4.2262
2.2665	0.453	4530	4.2409
2.2154	0.454	4540	4.2517
2.5899	0.455	4550	4.2381
1.9901	0.456	4560	4.2297
2.2154	0.457	4570	4.2134
2.2755	0.458	4580	4.2225
2.058	0.459	4590	4.2317
2.1179	0.46	4600	4.2195
2.1612	0.461	4610	4.2236
2.216	0.462	4620	4.2361
2.2586	0.463	4630	4.2021
2.248	0.464	4640	4.1822
2.3572	0.465	4650	4.1846
2.433	0.466	4660	4.1702
2.3894	0.467	4670	4.1767
2.2607	0.468	4680	4.1616
2.2147	0.469	4690	4.1733
2.4196	0.47	4700	4.1914
2.1684	0.471	4710	4.1864
2.1798	0.472	4720	4.1846
1.993	0.473	4730	4.1924
2.2485	0.474	4740	4.1609
2.1314	0.475	4750	4.1687
2.2203	0.476	4760	4.1455
2.1302	0.477	4770	4.1401
1.8882	0.478	4780	4.1852
2.2623	0.479	4790	4.1605
2.1286	0.48	4800	4.1304
2.1561	0.481	4810	4.1712
2.0941	0.482	4820	4.1690
2.012	0.483	4830	4.1525
1.9477	0.484	4840	4.1541
1.9873	0.485	4850	4.1763
2.3578	0.486	4860	4.1240
2.3894	0.487	4870	4.1102
2.0092	0.488	4880	4.1423
2.0482	0.489	4890	4.1301
2.0077	0.49	4900	4.1295
1.9114	0.491	4910	4.1474
2.1172	0.492	4920	4.1382
1.9315	0.493	4930	4.1264
2.1044	0.494	4940	4.1064
1.976	0.495	4950	4.0905
2.1449	0.496	4960	4.1133
2.1131	0.497	4970	4.1138
2.004	0.498	4980	4.1066
2.0212	0.499	4990	4.0998
2.1008	0.5	5000	4.1110
2.1145	0.501	5010	4.1178
2.1154	0.502	5020	4.0981
2.0931	0.503	5030	4.0863
2.0954	0.504	5040	4.0770
2.1068	0.505	5050	4.0761
1.8811	0.506	5060	4.0879
1.9368	0.507	5070	4.0992
2.1116	0.508	5080	4.0958
2.2019	0.509	5090	4.0719
2.0935	0.51	5100	4.0725
2.0152	0.511	5110	4.0679
2.0157	0.512	5120	4.0963
1.8603	0.513	5130	4.1048
2.1029	0.514	5140	4.0793
1.9495	0.515	5150	4.0696
1.746	0.516	5160	4.1178
2.0436	0.517	5170	4.0839
1.8402	0.518	5180	4.0689
1.9393	0.519	5190	4.0503
1.9576	0.52	5200	4.0582
1.9155	0.521	5210	4.0616
1.8562	0.522	5220	4.0770
1.772	0.523	5230	4.0903
1.8693	0.524	5240	4.0822
1.7747	0.525	5250	4.0838
1.8474	0.526	5260	4.0671
2.1497	0.527	5270	4.0611
1.9337	0.528	5280	4.0672
2.0366	0.529	5290	4.0475
1.9566	0.53	5300	4.0354
2.1054	0.531	5310	4.0429
1.7734	0.532	5320	4.0447
1.965	0.533	5330	4.0418
2.085	0.534	5340	4.0313
2.0969	0.535	5350	4.0274
1.8137	0.536	5360	4.0533
1.9213	0.537	5370	4.0520
1.699	0.538	5380	4.0431
1.7902	0.539	5390	4.0378
1.8461	0.54	5400	4.0396
2.0112	0.541	5410	4.0004
1.9799	0.542	5420	4.0015
1.9226	0.543	5430	4.0064
1.8766	0.544	5440	4.0116
2.0135	0.545	5450	4.0020
1.8534	0.546	5460	4.0064
1.917	0.547	5470	3.9968
1.9525	0.548	5480	4.0079
1.7654	0.549	5490	4.0143
1.7959	0.55	5500	4.0287
1.6686	0.551	5510	4.0363
1.6723	0.552	5520	4.0035
1.7373	0.553	5530	4.0136
1.8105	0.554	5540	3.9967
1.7868	0.555	5550	4.0068
1.8073	0.556	5560	4.0235
1.9028	0.557	5570	4.0104
1.6599	0.558	5580	4.0055
1.8416	0.559	5590	4.0012
1.921	0.56	5600	4.0009
1.8473	0.561	5610	3.9979
1.6912	0.562	5620	4.0097
1.7104	0.563	5630	4.0030
1.8125	0.564	5640	3.9858
1.8455	0.565	5650	3.9806
1.7542	0.566	5660	3.9784
1.8892	0.567	5670	3.9925
1.6582	0.568	5680	3.9845
1.7345	0.569	5690	4.0067
1.8135	0.57	5700	3.9958
1.8084	0.571	5710	3.9842
1.7094	0.572	5720	3.9894
1.6312	0.573	5730	3.9810
1.7423	0.574	5740	3.9770
1.6973	0.575	5750	3.9879
1.7027	0.576	5760	3.9789
1.8296	0.577	5770	3.9776
1.6769	0.578	5780	3.9721
1.5548	0.579	5790	3.9845
1.6085	0.58	5800	4.0000
1.7654	0.581	5810	3.9506
1.7707	0.582	5820	3.9530
1.7545	0.583	5830	3.9648
1.5998	0.584	5840	3.9925
1.5918	0.585	5850	3.9717
1.8273	0.586	5860	3.9649
1.6181	0.587	5870	3.9836
1.5624	0.588	5880	3.9633
1.6318	0.589	5890	3.9746
1.6677	0.59	5900	3.9867
1.7551	0.591	5910	3.9526
1.6629	0.592	5920	3.9768
1.7673	0.593	5930	3.9686
1.5675	0.594	5940	3.9927
1.6911	0.595	5950	3.9832
1.7887	0.596	5960	3.9560
1.6528	0.597	5970	3.9487
1.6431	0.598	5980	3.9553
1.6284	0.599	5990	3.9321
1.784	0.6	6000	3.9300
1.6791	0.601	6010	3.9642
1.7124	0.602	6020	3.9722
1.7609	0.603	6030	3.9663
1.6781	0.604	6040	3.9558
1.6359	0.605	6050	3.9528
1.6021	0.606	6060	3.9504
1.6271	0.607	6070	3.9340
1.7003	0.608	6080	3.9202
1.8715	0.609	6090	3.9358
1.6876	0.61	6100	3.9306
1.7108	0.611	6110	3.9367
1.6943	0.612	6120	3.9411
1.5966	0.613	6130	3.9421
1.6138	0.614	6140	3.9307
1.5829	0.615	6150	3.9405
1.6614	0.616	6160	3.9157
1.5733	0.617	6170	3.9490
1.4604	0.618	6180	3.9361
1.4501	0.619	6190	3.9401
1.5753	0.62	6200	3.9473
1.6593	0.621	6210	3.9425
1.5561	0.622	6220	3.9386
1.4955	0.623	6230	3.9412
1.5925	0.624	6240	3.9265
1.5622	0.625	6250	3.9471
1.5001	0.626	6260	3.9177
1.7508	0.627	6270	3.9125
1.7536	0.628	6280	3.9191
1.551	0.629	6290	3.9306
1.6486	0.63	6300	3.9180
1.5344	0.631	6310	3.9282
1.5419	0.632	6320	3.9304
1.5617	0.633	6330	3.9196
1.7536	0.634	6340	3.9111
1.589	0.635	6350	3.9327
1.6411	0.636	6360	3.9190
1.6056	0.637	6370	3.9288
1.5037	0.638	6380	3.9282
1.5577	0.639	6390	3.9247
1.6489	0.64	6400	3.9278
1.471	0.641	6410	3.9233
1.7566	0.642	6420	3.8879
1.6957	0.643	6430	3.8987
1.3941	0.644	6440	3.9220
1.4225	0.645	6450	3.8974
1.4719	0.646	6460	3.9173
1.4352	0.647	6470	3.9120
1.4844	0.648	6480	3.9108
1.6576	0.649	6490	3.9273
1.516	0.65	6500	3.9145
1.5373	0.651	6510	3.9183
1.4004	0.652	6520	3.9233
1.4519	0.653	6530	3.9044
1.6284	0.654	6540	3.9017
1.5553	0.655	6550	3.8956
1.4852	0.656	6560	3.9192
1.5767	0.657	6570	3.9013
1.6317	0.658	6580	3.8878
1.5306	0.659	6590	3.8964
1.5386	0.66	6600	3.8858
1.4967	0.661	6610	3.8977
1.5523	0.662	6620	3.8719
1.5526	0.663	6630	3.8862
1.5022	0.664	6640	3.8924
1.5227	0.665	6650	3.9005
1.5673	0.666	6660	3.8962
1.4177	0.667	6670	3.9010
1.5379	0.668	6680	3.9022
1.3781	0.669	6690	3.8830
1.5553	0.67	6700	3.8835
1.5428	0.671	6710	3.8784
1.5307	0.672	6720	3.8654
1.5443	0.673	6730	3.8726
1.572	0.674	6740	3.8723
1.4443	0.675	6750	3.8802
1.4983	0.676	6760	3.8778
1.6395	0.677	6770	3.8702
1.4878	0.678	6780	3.8698
1.3684	0.679	6790	3.8866
1.6223	0.68	6800	3.8685
1.4744	0.681	6810	3.8569
1.4779	0.682	6820	3.8994
1.4175	0.683	6830	3.8845
1.533	0.684	6840	3.8973
1.5796	0.685	6850	3.8739
1.5348	0.686	6860	3.8522
1.5479	0.687	6870	3.8573
1.5132	0.688	6880	3.8525
1.3636	0.689	6890	3.8609
1.5992	0.69	6900	3.8618
1.5323	0.691	6910	3.8735
1.4068	0.692	6920	3.8608
1.4023	0.693	6930	3.8591
1.3799	0.694	6940	3.8871
1.452	0.695	6950	3.8551
1.5322	0.696	6960	3.8810
1.5245	0.697	6970	3.8622
1.435	0.698	6980	3.8574
1.4849	0.699	6990	3.8608
1.3309	0.7	7000	3.8538
1.3596	0.701	7010	3.8474
1.496	0.702	7020	3.8652
1.3853	0.703	7030	3.8590
1.3671	0.704	7040	3.8722
1.4362	0.705	7050	3.8484
1.4251	0.706	7060	3.8544
1.3982	0.707	7070	3.8701
1.4628	0.708	7080	3.8810
1.3307	0.709	7090	3.8680
1.3799	0.71	7100	3.8772
1.4115	0.711	7110	3.8774
1.4065	0.712	7120	3.8752
1.288	0.713	7130	3.8846
1.3547	0.714	7140	3.8743
1.4197	0.715	7150	3.8773
1.3924	0.716	7160	3.8591
1.4369	0.717	7170	3.8586
1.4426	0.718	7180	3.8526
1.4369	0.719	7190	3.8458
1.3719	0.72	7200	3.8671
1.4219	0.721	7210	3.8770
1.5038	0.722	7220	3.8694
1.4096	0.723	7230	3.8758
1.3372	0.724	7240	3.8517
1.3688	0.725	7250	3.8778
1.2378	0.726	7260	3.8714
1.3906	0.727	7270	3.8598
1.3598	0.728	7280	3.8579
1.3902	0.729	7290	3.8598
1.4013	0.73	7300	3.8519
1.406	0.731	7310	3.8430
1.3771	0.732	7320	3.8530
1.3977	0.733	7330	3.8601
1.3891	0.734	7340	3.8602
1.3085	0.735	7350	3.8707
1.2285	0.736	7360	3.8723
1.3097	0.737	7370	3.8502
1.3648	0.738	7380	3.8629
1.4576	0.739	7390	3.8491
1.3136	0.74	7400	3.8824
1.2518	0.741	7410	3.8756
1.4524	0.742	7420	3.8423
1.3969	0.743	7430	3.8411
1.3776	0.744	7440	3.8509
1.3915	0.745	7450	3.8595
1.3721	0.746	7460	3.8656
1.3955	0.747	7470	3.8613
1.2734	0.748	7480	3.8572
1.3972	0.749	7490	3.8506
1.3601	0.75	7500	3.8551
1.3121	0.751	7510	3.8541
1.4033	0.752	7520	3.8517
1.3927	0.753	7530	3.8531
1.4111	0.754	7540	3.8590
1.3176	0.755	7550	3.8677
1.3108	0.756	7560	3.8660
1.3579	0.757	7570	3.8639
1.2712	0.758	7580	3.8562
1.3528	0.759	7590	3.8630
1.2751	0.76	7600	3.8457
1.2843	0.761	7610	3.8412
1.4342	0.762	7620	3.8312
1.2923	0.763	7630	3.8313
1.2928	0.764	7640	3.8377
1.3991	0.765	7650	3.8341
1.3392	0.766	7660	3.8296
1.4142	0.767	7670	3.8330
1.3003	0.768	7680	3.8433
1.2786	0.769	7690	3.8480
1.3252	0.77	7700	3.8272
1.268	0.771	7710	3.8491
1.3003	0.772	7720	3.8317
1.1916	0.773	7730	3.8259
1.2441	0.774	7740	3.8372
1.3544	0.775	7750	3.8532
1.3366	0.776	7760	3.8574
1.3176	0.777	7770	3.8542
1.4013	0.778	7780	3.8443
1.3959	0.779	7790	3.8437
1.3284	0.78	7800	3.8346
1.3716	0.781	7810	3.8347
1.3457	0.782	7820	3.8284
1.3317	0.783	7830	3.8316
1.3212	0.784	7840	3.8416
1.3497	0.785	7850	3.8273
1.3576	0.786	7860	3.8407
1.3531	0.787	7870	3.8393
1.2701	0.788	7880	3.8504
1.3198	0.789	7890	3.8539
1.3783	0.79	7900	3.8297
1.2354	0.791	7910	3.8391
1.3324	0.792	7920	3.8292
1.3203	0.793	7930	3.8334
1.3253	0.794	7940	3.8320
1.191	0.795	7950	3.8647
1.2396	0.796	7960	3.8496
1.2722	0.797	7970	3.8371
1.3823	0.798	7980	3.8307
1.3459	0.799	7990	3.8302
1.3508	0.8	8000	3.8543
1.3335	0.801	8010	3.8508
1.2138	0.802	8020	3.8359
1.3548	0.803	8030	3.8356
1.3702	0.804	8040	3.8311
1.241	0.805	8050	3.8369
1.3318	0.806	8060	3.8267
1.3235	0.807	8070	3.8281
1.333	0.808	8080	3.8328
1.3423	0.809	8090	3.8448
1.3179	0.81	8100	3.8245
1.3776	0.811	8110	3.8232
1.3662	0.812	8120	3.8304
1.2795	0.813	8130	3.8361
1.1821	0.814	8140	3.8349
1.3036	0.815	8150	3.8068
1.3673	0.816	8160	3.8173
1.3004	0.817	8170	3.8354
1.3209	0.818	8180	3.8290
1.2968	0.819	8190	3.8300
1.2513	0.82	8200	3.8491
1.246	0.821	8210	3.8453
1.2457	0.822	8220	3.8367
1.3327	0.823	8230	3.8362
1.3708	0.824	8240	3.8351
1.2707	0.825	8250	3.8311
1.3164	0.826	8260	3.8411
1.2163	0.827	8270	3.8408
1.3469	0.828	8280	3.8288
1.2658	0.829	8290	3.8248
1.2693	0.83	8300	3.8187
1.3177	0.831	8310	3.8308
1.3119	0.832	8320	3.8332
1.2206	0.833	8330	3.8384
1.2535	0.834	8340	3.8443
1.2741	0.835	8350	3.8313
1.2692	0.836	8360	3.8348
1.2588	0.837	8370	3.8364
1.3957	0.838	8380	3.8188
1.2313	0.839	8390	3.8289
1.2882	0.84	8400	3.8311
1.3057	0.841	8410	3.8203
1.2792	0.842	8420	3.8373
1.3375	0.843	8430	3.8239
1.2899	0.844	8440	3.8188
1.2099	0.845	8450	3.8367
1.2795	0.846	8460	3.8307
1.3613	0.847	8470	3.8171
1.3261	0.848	8480	3.8269
1.3025	0.849	8490	3.8275
1.2972	0.85	8500	3.8367
1.1742	0.851	8510	3.8353
1.1846	0.852	8520	3.8483
1.2828	0.853	8530	3.8264
1.3182	0.854	8540	3.8296
1.1832	0.855	8550	3.8258
1.233	0.856	8560	3.8259
1.3038	0.857	8570	3.8205
1.2528	0.858	8580	3.8328
1.3166	0.859	8590	3.8312
1.2779	0.86	8600	3.8264
1.2742	0.861	8610	3.8322
1.2016	0.862	8620	3.8413
1.2093	0.863	8630	3.8355
1.2256	0.864	8640	3.8366
1.2202	0.865	8650	3.8301
1.2817	0.866	8660	3.8328
1.2817	0.867	8670	3.8253
1.1664	0.868	8680	3.8271
1.2658	0.869	8690	3.8287
1.2247	0.87	8700	3.8225
1.1852	0.871	8710	3.8337
1.3027	0.872	8720	3.8434
1.2975	0.873	8730	3.8399
1.2083	0.874	8740	3.8475
1.3507	0.875	8750	3.8184
1.1542	0.876	8760	3.8303
1.2419	0.877	8770	3.8347
1.296	0.878	8780	3.8257
1.292	0.879	8790	3.8159
1.1907	0.88	8800	3.8131
1.3122	0.881	8810	3.8105
1.2661	0.882	8820	3.8333
1.2656	0.883	8830	3.8131
1.3465	0.884	8840	3.8109
1.2222	0.885	8850	3.8176
1.2893	0.886	8860	3.8175
1.2303	0.887	8870	3.8453
1.2243	0.888	8880	3.8286
1.2214	0.889	8890	3.8326
1.2331	0.89	8900	3.8414
1.2845	0.891	8910	3.8380
1.2194	0.892	8920	3.8223
1.2243	0.893	8930	3.8418
1.184	0.894	8940	3.8470
1.2281	0.895	8950	3.8136
1.2289	0.896	8960	3.8211
1.1995	0.897	8970	3.8204
1.187	0.898	8980	3.8300
1.1981	0.899	8990	3.8320
1.2387	0.9	9000	3.8276
1.2377	0.901	9010	3.8287
1.2821	0.902	9020	3.8271
1.3417	0.903	9030	3.8232
1.4299	0.904	9040	3.8170
1.2262	0.905	9050	3.8238
1.3383	0.906	9060	3.8245
1.3091	0.907	9070	3.8152
1.1738	0.908	9080	3.8229
1.1697	0.909	9090	3.8354
1.2209	0.91	9100	3.8108
1.2125	0.911	9110	3.8141
1.2135	0.912	9120	3.8360
1.1404	0.913	9130	3.8310
1.2161	0.914	9140	3.8289
1.1924	0.915	9150	3.8365
1.1901	0.916	9160	3.8359
1.2155	0.917	9170	3.8165
1.2111	0.918	9180	3.8243
1.3481	0.919	9190	3.8391
1.1716	0.92	9200	3.8320
1.2404	0.921	9210	3.8296
1.1468	0.922	9220	3.8268
1.3044	0.923	9230	3.8205
1.2892	0.924	9240	3.8174
1.2333	0.925	9250	3.8222
1.2826	0.926	9260	3.8272
1.1637	0.927	9270	3.8215
1.1579	0.928	9280	3.8255
1.199	0.929	9290	3.8297
1.1366	0.93	9300	3.8326
1.2473	0.931	9310	3.8304
1.2459	0.932	9320	3.8236
1.1259	0.933	9330	3.8293
1.1531	0.934	9340	3.8406
1.2119	0.935	9350	3.8305
1.3924	0.936	9360	3.8213
1.2839	0.937	9370	3.8157
1.2187	0.938	9380	3.8140
1.1793	0.939	9390	3.8168
1.2865	0.94	9400	3.8105
1.1805	0.941	9410	3.8076
1.2965	0.942	9420	3.8178
1.2113	0.943	9430	3.8291
1.2204	0.944	9440	3.8340
1.1904	0.945	9450	3.8227
1.2431	0.946	9460	3.8080
1.3614	0.947	9470	3.8102
1.2818	0.948	9480	3.8149
1.1449	0.949	9490	3.8210
1.2737	0.95	9500	3.8226
1.1359	0.951	9510	3.8258
1.2892	0.952	9520	3.8243
1.3162	0.953	9530	3.8191
1.2826	0.954	9540	3.8221
1.1769	0.955	9550	3.8258
1.2128	0.956	9560	3.8310
1.1731	0.957	9570	3.8300
1.2822	0.958	9580	3.8262
1.2047	0.959	9590	3.8289
1.2049	0.96	9600	3.8296
1.248	0.961	9610	3.8303
1.182	0.962	9620	3.8289
1.1664	0.963	9630	3.8288
1.1832	0.964	9640	3.8336
1.1865	0.965	9650	3.8360
1.2062	0.966	9660	3.8366
1.2313	0.967	9670	3.8347
1.2191	0.968	9680	3.8321
1.2971	0.969	9690	3.8302
1.3044	0.97	9700	3.8281
1.1974	0.971	9710	3.8225
1.2238	0.972	9720	3.8217
1.2993	0.973	9730	3.8200
1.3517	0.974	9740	3.8172
1.2726	0.975	9750	3.8197
1.1928	0.976	9760	3.8203
1.1851	0.977	9770	3.8242
1.224	0.978	9780	3.8267
1.2013	0.979	9790	3.8321
1.2403	0.98	9800	3.8302
1.2332	0.981	9810	3.8292
1.2009	0.982	9820	3.8287
1.2405	0.983	9830	3.8273
1.2437	0.984	9840	3.8261
1.2705	0.985	9850	3.8262
1.1487	0.986	9860	3.8236
1.1559	0.987	9870	3.8261
1.1484	0.988	9880	3.8260
1.166	0.989	9890	3.8266
1.1824	0.99	9900	3.8260
1.1619	0.991	9910	3.8272
1.1429	0.992	9920	3.8262
1.1452	0.993	9930	3.8262
1.1366	0.994	9940	3.8258
1.1314	0.995	9950	3.8267
1.2708	0.996	9960	3.8291
1.2712	0.997	9970	3.8273
1.1591	0.998	9980	3.8275
1.2451	0.999	9990	3.8274
1.3344	1.0	10000	3.8262

Framework versions

• Transformers 4.44.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1