Se124M500KInfPrompt_EOS

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3506

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-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.8274	0.0044	20	2.5097
2.8217	0.0088	40	2.5069
2.8191	0.0132	60	2.4970
2.79	0.0176	80	2.4724
2.7185	0.0220	100	2.4241
2.6593	0.0264	120	2.3585
2.5596	0.0307	140	2.2658
2.3996	0.0351	160	2.1526
2.2752	0.0395	180	2.0096
2.1117	0.0439	200	1.8505
1.8995	0.0483	220	1.6356
1.6694	0.0527	240	1.3914
1.4535	0.0571	260	1.1593
1.2244	0.0615	280	0.9593
1.0506	0.0659	300	0.8271
0.9234	0.0703	320	0.7381
0.8293	0.0747	340	0.6670
0.7586	0.0791	360	0.6094
0.6988	0.0835	380	0.5666
0.6418	0.0878	400	0.5376
0.608	0.0922	420	0.5185
0.5688	0.0966	440	0.5034
0.5613	0.1010	460	0.4926
0.5393	0.1054	480	0.4805
0.5314	0.1098	500	0.4737
0.5283	0.1142	520	0.4674
0.5129	0.1186	540	0.4645
0.5104	0.1230	560	0.4619
0.5057	0.1274	580	0.4576
0.4965	0.1318	600	0.4522
0.4948	0.1362	620	0.4526
0.4824	0.1406	640	0.4491
0.4858	0.1449	660	0.4459
0.4888	0.1493	680	0.4397
0.475	0.1537	700	0.4384
0.4751	0.1581	720	0.4390
0.4803	0.1625	740	0.4352
0.4744	0.1669	760	0.4328
0.4767	0.1713	780	0.4317
0.4638	0.1757	800	0.4304
0.4729	0.1801	820	0.4246
0.4627	0.1845	840	0.4258
0.4662	0.1889	860	0.4225
0.4577	0.1933	880	0.4238
0.4592	0.1977	900	0.4223
0.4544	0.2020	920	0.4181
0.4613	0.2064	940	0.4158
0.4462	0.2108	960	0.4172
0.458	0.2152	980	0.4147
0.4456	0.2196	1000	0.4159
0.4484	0.2240	1020	0.4100
0.4451	0.2284	1040	0.4108
0.4458	0.2328	1060	0.4119
0.4439	0.2372	1080	0.4086
0.4465	0.2416	1100	0.4062
0.4428	0.2460	1120	0.4053
0.4507	0.2504	1140	0.4074
0.4528	0.2547	1160	0.4010
0.4366	0.2591	1180	0.4025
0.446	0.2635	1200	0.4041
0.4404	0.2679	1220	0.4031
0.4378	0.2723	1240	0.4032
0.4434	0.2767	1260	0.4037
0.4364	0.2811	1280	0.4025
0.4417	0.2855	1300	0.3989
0.4371	0.2899	1320	0.3949
0.4356	0.2943	1340	0.3982
0.433	0.2987	1360	0.3965
0.4406	0.3031	1380	0.3952
0.4342	0.3075	1400	0.3935
0.4382	0.3118	1420	0.3944
0.429	0.3162	1440	0.3926
0.4318	0.3206	1460	0.3919
0.4254	0.3250	1480	0.3902
0.4305	0.3294	1500	0.3913
0.4333	0.3338	1520	0.3904
0.4306	0.3382	1540	0.3879
0.4281	0.3426	1560	0.3881
0.4291	0.3470	1580	0.3891
0.4287	0.3514	1600	0.3893
0.436	0.3558	1620	0.3876
0.4237	0.3602	1640	0.3858
0.4228	0.3646	1660	0.3851
0.4256	0.3689	1680	0.3863
0.4215	0.3733	1700	0.3848
0.4296	0.3777	1720	0.3843
0.4239	0.3821	1740	0.3840
0.4211	0.3865	1760	0.3839
0.4268	0.3909	1780	0.3825
0.426	0.3953	1800	0.3796
0.4192	0.3997	1820	0.3847
0.423	0.4041	1840	0.3819
0.4256	0.4085	1860	0.3819
0.4216	0.4129	1880	0.3813
0.424	0.4173	1900	0.3796
0.4201	0.4217	1920	0.3784
0.4224	0.4260	1940	0.3811
0.419	0.4304	1960	0.3799
0.421	0.4348	1980	0.3790
0.4208	0.4392	2000	0.3779
0.4175	0.4436	2020	0.3784
0.4213	0.4480	2040	0.3769
0.4233	0.4524	2060	0.3761
0.4165	0.4568	2080	0.3763
0.4164	0.4612	2100	0.3783
0.4212	0.4656	2120	0.3740
0.4216	0.4700	2140	0.3741
0.413	0.4744	2160	0.3744
0.4181	0.4788	2180	0.3751
0.4178	0.4831	2200	0.3760
0.4105	0.4875	2220	0.3730
0.4159	0.4919	2240	0.3729
0.4177	0.4963	2260	0.3755
0.4149	0.5007	2280	0.3746
0.4184	0.5051	2300	0.3741
0.4141	0.5095	2320	0.3745
0.4123	0.5139	2340	0.3723
0.4103	0.5183	2360	0.3738
0.4136	0.5227	2380	0.3741
0.4109	0.5271	2400	0.3735
0.4118	0.5315	2420	0.3717
0.4103	0.5359	2440	0.3723
0.41	0.5402	2460	0.3711
0.4079	0.5446	2480	0.3756
0.4141	0.5490	2500	0.3730
0.4106	0.5534	2520	0.3710
0.4145	0.5578	2540	0.3710
0.4094	0.5622	2560	0.3710
0.4149	0.5666	2580	0.3717
0.4103	0.5710	2600	0.3710
0.4144	0.5754	2620	0.3693
0.4146	0.5798	2640	0.3700
0.4108	0.5842	2660	0.3708
0.409	0.5886	2680	0.3695
0.4017	0.5930	2700	0.3688
0.4117	0.5973	2720	0.3704
0.4167	0.6017	2740	0.3691
0.4073	0.6061	2760	0.3679
0.409	0.6105	2780	0.3683
0.408	0.6149	2800	0.3690
0.4101	0.6193	2820	0.3679
0.4097	0.6237	2840	0.3687
0.4063	0.6281	2860	0.3688
0.4092	0.6325	2880	0.3677
0.4116	0.6369	2900	0.3683
0.411	0.6413	2920	0.3682
0.4045	0.6457	2940	0.3687
0.4086	0.6500	2960	0.3676
0.4016	0.6544	2980	0.3665
0.4054	0.6588	3000	0.3671
0.4054	0.6632	3020	0.3667
0.4034	0.6676	3040	0.3665
0.4068	0.6720	3060	0.3673
0.4093	0.6764	3080	0.3670
0.4109	0.6808	3100	0.3665
0.4091	0.6852	3120	0.3655
0.4098	0.6896	3140	0.3673
0.4042	0.6940	3160	0.3668
0.4015	0.6984	3180	0.3676
0.4055	0.7028	3200	0.3674
0.3998	0.7071	3220	0.3670
0.4009	0.7115	3240	0.3659
0.401	0.7159	3260	0.3646
0.4028	0.7203	3280	0.3658
0.4017	0.7247	3300	0.3647
0.4045	0.7291	3320	0.3652
0.4016	0.7335	3340	0.3665
0.3985	0.7379	3360	0.3651
0.4026	0.7423	3380	0.3653
0.4008	0.7467	3400	0.3640
0.3993	0.7511	3420	0.3641
0.4045	0.7555	3440	0.3650
0.4031	0.7599	3460	0.3653
0.3996	0.7642	3480	0.3638
0.3985	0.7686	3500	0.3655
0.3988	0.7730	3520	0.3641
0.3985	0.7774	3540	0.3643
0.4007	0.7818	3560	0.3660
0.4007	0.7862	3580	0.3634
0.4001	0.7906	3600	0.3632
0.3978	0.7950	3620	0.3644
0.3995	0.7994	3640	0.3635
0.3978	0.8038	3660	0.3631
0.3997	0.8082	3680	0.3648
0.396	0.8126	3700	0.3643
0.3985	0.8170	3720	0.3656
0.3968	0.8213	3740	0.3650
0.3948	0.8257	3760	0.3638
0.3932	0.8301	3780	0.3650
0.3979	0.8345	3800	0.3639
0.401	0.8389	3820	0.3637
0.3955	0.8433	3840	0.3626
0.3969	0.8477	3860	0.3631
0.4007	0.8521	3880	0.3640
0.3963	0.8565	3900	0.3637
0.393	0.8609	3920	0.3626
0.3945	0.8653	3940	0.3624
0.3915	0.8697	3960	0.3643
0.3972	0.8741	3980	0.3637
0.393	0.8784	4000	0.3632
0.3942	0.8828	4020	0.3620
0.3905	0.8872	4040	0.3623
0.3938	0.8916	4060	0.3620
0.3957	0.8960	4080	0.3621
0.3948	0.9004	4100	0.3618
0.3908	0.9048	4120	0.3626
0.3959	0.9092	4140	0.3641
0.3917	0.9136	4160	0.3623
0.3928	0.9180	4180	0.3615
0.3896	0.9224	4200	0.3634
0.3895	0.9268	4220	0.3615
0.3926	0.9312	4240	0.3612
0.3912	0.9355	4260	0.3620
0.3918	0.9399	4280	0.3629
0.3949	0.9443	4300	0.3619
0.3955	0.9487	4320	0.3616
0.39	0.9531	4340	0.3622
0.3856	0.9575	4360	0.3623
0.3926	0.9619	4380	0.3612
0.3903	0.9663	4400	0.3609
0.3919	0.9707	4420	0.3619
0.392	0.9751	4440	0.3615
0.3946	0.9795	4460	0.3608
0.3886	0.9839	4480	0.3618
0.3925	0.9883	4500	0.3611
0.3937	0.9926	4520	0.3607
0.3892	0.9970	4540	0.3608
0.3875	1.0013	4560	0.3610
0.3875	1.0057	4580	0.3602
0.3876	1.0101	4600	0.3604
0.3866	1.0145	4620	0.3609
0.3875	1.0189	4640	0.3606
0.3825	1.0233	4660	0.3619
0.3803	1.0277	4680	0.3604
0.3855	1.0321	4700	0.3602
0.3831	1.0365	4720	0.3600
0.3878	1.0408	4740	0.3603
0.3881	1.0452	4760	0.3605
0.384	1.0496	4780	0.3592
0.3866	1.0540	4800	0.3604
0.382	1.0584	4820	0.3608
0.3836	1.0628	4840	0.3587
0.3912	1.0672	4860	0.3596
0.3897	1.0716	4880	0.3604
0.3828	1.0760	4900	0.3606
0.3868	1.0804	4920	0.3594
0.3891	1.0848	4940	0.3598
0.385	1.0892	4960	0.3599
0.3836	1.0936	4980	0.3592
0.3866	1.0979	5000	0.3595
0.3817	1.1023	5020	0.3602
0.3786	1.1067	5040	0.3601
0.3814	1.1111	5060	0.3584
0.3868	1.1155	5080	0.3591
0.3802	1.1199	5100	0.3603
0.384	1.1243	5120	0.3606
0.3833	1.1287	5140	0.3591
0.3795	1.1331	5160	0.3598
0.3872	1.1375	5180	0.3595
0.3864	1.1419	5200	0.3594
0.3748	1.1463	5220	0.3591
0.3778	1.1507	5240	0.3590
0.3844	1.1550	5260	0.3595
0.3796	1.1594	5280	0.3585
0.3824	1.1638	5300	0.3594
0.3815	1.1682	5320	0.3580
0.3803	1.1726	5340	0.3589
0.3775	1.1770	5360	0.3582
0.3765	1.1814	5380	0.3583
0.3831	1.1858	5400	0.3592
0.3862	1.1902	5420	0.3589
0.3791	1.1946	5440	0.3586
0.3776	1.1990	5460	0.3572
0.3805	1.2034	5480	0.3587
0.3815	1.2078	5500	0.3594
0.3848	1.2121	5520	0.3586
0.3825	1.2165	5540	0.3589
0.3778	1.2209	5560	0.3573
0.3775	1.2253	5580	0.3578
0.3791	1.2297	5600	0.3584
0.3764	1.2341	5620	0.3578
0.3767	1.2385	5640	0.3581
0.3804	1.2429	5660	0.3573
0.3781	1.2473	5680	0.3579
0.3796	1.2517	5700	0.3581
0.3739	1.2561	5720	0.3581
0.3801	1.2605	5740	0.3571
0.3828	1.2649	5760	0.3579
0.3802	1.2692	5780	0.3575
0.3817	1.2736	5800	0.3567
0.3793	1.2780	5820	0.3585
0.3769	1.2824	5840	0.3582
0.3759	1.2868	5860	0.3573
0.3805	1.2912	5880	0.3562
0.374	1.2956	5900	0.3563
0.3768	1.3000	5920	0.3575
0.3813	1.3044	5940	0.3565
0.375	1.3088	5960	0.3571
0.379	1.3132	5980	0.3574
0.3791	1.3176	6000	0.3570
0.3797	1.3220	6020	0.3575
0.379	1.3263	6040	0.3561
0.3753	1.3307	6060	0.3572
0.379	1.3351	6080	0.3577
0.3751	1.3395	6100	0.3574
0.3752	1.3439	6120	0.3565
0.3747	1.3483	6140	0.3574
0.3789	1.3527	6160	0.3567
0.3777	1.3571	6180	0.3568
0.3735	1.3615	6200	0.3576
0.379	1.3659	6220	0.3565
0.3771	1.3703	6240	0.3567
0.3727	1.3747	6260	0.3571
0.374	1.3790	6280	0.3569
0.3747	1.3834	6300	0.3564
0.3727	1.3878	6320	0.3559
0.3796	1.3922	6340	0.3564
0.3782	1.3966	6360	0.3559
0.3729	1.4010	6380	0.3575
0.3755	1.4054	6400	0.3560
0.3713	1.4098	6420	0.3571
0.3774	1.4142	6440	0.3577
0.3753	1.4186	6460	0.3557
0.3784	1.4230	6480	0.3567
0.3809	1.4274	6500	0.3555
0.3712	1.4318	6520	0.3559
0.3734	1.4361	6540	0.3564
0.3739	1.4405	6560	0.3560
0.373	1.4449	6580	0.3559
0.3778	1.4493	6600	0.3565
0.3732	1.4537	6620	0.3571
0.376	1.4581	6640	0.3555
0.3785	1.4625	6660	0.3558
0.3755	1.4669	6680	0.3571
0.3747	1.4713	6700	0.3548
0.3764	1.4757	6720	0.3560
0.3788	1.4801	6740	0.3551
0.3734	1.4845	6760	0.3560
0.3755	1.4889	6780	0.3553
0.3706	1.4932	6800	0.3557
0.3762	1.4976	6820	0.3547
0.374	1.5020	6840	0.3558
0.3756	1.5064	6860	0.3557
0.3759	1.5108	6880	0.3552
0.3718	1.5152	6900	0.3560
0.3755	1.5196	6920	0.3559
0.3753	1.5240	6940	0.3550
0.3764	1.5284	6960	0.3558
0.3749	1.5328	6980	0.3545
0.3749	1.5372	7000	0.3550
0.3701	1.5416	7020	0.3557
0.3698	1.5460	7040	0.3554
0.3741	1.5503	7060	0.3554
0.3763	1.5547	7080	0.3554
0.3717	1.5591	7100	0.3541
0.3697	1.5635	7120	0.3549
0.3729	1.5679	7140	0.3539
0.3737	1.5723	7160	0.3551
0.3753	1.5767	7180	0.3550
0.3738	1.5811	7200	0.3550
0.3726	1.5855	7220	0.3543
0.3762	1.5899	7240	0.3551
0.3697	1.5943	7260	0.3563
0.3732	1.5987	7280	0.3543
0.3705	1.6031	7300	0.3548
0.3745	1.6074	7320	0.3544
0.3723	1.6118	7340	0.3536
0.3753	1.6162	7360	0.3532
0.3733	1.6206	7380	0.3547
0.3743	1.6250	7400	0.3536
0.3703	1.6294	7420	0.3544
0.3751	1.6338	7440	0.3540
0.3728	1.6382	7460	0.3535
0.3692	1.6426	7480	0.3541
0.3726	1.6470	7500	0.3539
0.3734	1.6514	7520	0.3545
0.3707	1.6558	7540	0.3538
0.3737	1.6602	7560	0.3545
0.3721	1.6645	7580	0.3542
0.373	1.6689	7600	0.3541
0.372	1.6733	7620	0.3531
0.3736	1.6777	7640	0.3546
0.368	1.6821	7660	0.3548
0.3675	1.6865	7680	0.3541
0.3704	1.6909	7700	0.3536
0.3739	1.6953	7720	0.3546
0.3717	1.6997	7740	0.3545
0.3694	1.7041	7760	0.3540
0.3759	1.7085	7780	0.3536
0.3741	1.7129	7800	0.3533
0.375	1.7173	7820	0.3536
0.3745	1.7216	7840	0.3532
0.3673	1.7260	7860	0.3538
0.3756	1.7304	7880	0.3535
0.3693	1.7348	7900	0.3535
0.3712	1.7392	7920	0.3530
0.3731	1.7436	7940	0.3539
0.3722	1.7480	7960	0.3531
0.3697	1.7524	7980	0.3533
0.3684	1.7568	8000	0.3542
0.373	1.7612	8020	0.3537
0.3684	1.7656	8040	0.3543
0.3684	1.7700	8060	0.3535
0.3712	1.7743	8080	0.3540
0.3711	1.7787	8100	0.3530
0.3723	1.7831	8120	0.3539
0.3686	1.7875	8140	0.3544
0.3733	1.7919	8160	0.3534
0.373	1.7963	8180	0.3537
0.3701	1.8007	8200	0.3529
0.3751	1.8051	8220	0.3523
0.3744	1.8095	8240	0.3524
0.3757	1.8139	8260	0.3534
0.3714	1.8183	8280	0.3542
0.3719	1.8227	8300	0.3530
0.3725	1.8271	8320	0.3529
0.3707	1.8314	8340	0.3528
0.3704	1.8358	8360	0.3529
0.3718	1.8402	8380	0.3532
0.3729	1.8446	8400	0.3534
0.3674	1.8490	8420	0.3536
0.3706	1.8534	8440	0.3530
0.3683	1.8578	8460	0.3529
0.3695	1.8622	8480	0.3532
0.3721	1.8666	8500	0.3529
0.3716	1.8710	8520	0.3531
0.3704	1.8754	8540	0.3533
0.3686	1.8798	8560	0.3528
0.3721	1.8842	8580	0.3535
0.3715	1.8885	8600	0.3529
0.3659	1.8929	8620	0.3535
0.3757	1.8973	8640	0.3526
0.3711	1.9017	8660	0.3523
0.3729	1.9061	8680	0.3528
0.3729	1.9105	8700	0.3530
0.3725	1.9149	8720	0.3534
0.373	1.9193	8740	0.3526
0.3735	1.9237	8760	0.3527
0.3736	1.9281	8780	0.3530
0.3667	1.9325	8800	0.3527
0.3751	1.9369	8820	0.3524
0.3671	1.9413	8840	0.3522
0.3718	1.9456	8860	0.3528
0.3727	1.9500	8880	0.3518
0.3684	1.9544	8900	0.3523
0.3701	1.9588	8920	0.3528
0.3713	1.9632	8940	0.3522
0.3722	1.9676	8960	0.3531
0.3705	1.9720	8980	0.3520
0.3695	1.9764	9000	0.3518
0.3756	1.9808	9020	0.3524
0.3705	1.9852	9040	0.3528
0.3681	1.9896	9060	0.3524
0.3684	1.9940	9080	0.3526
0.3704	1.9984	9100	0.3525
0.3728	2.0026	9120	0.3516
0.3689	2.0070	9140	0.3525
0.3738	2.0114	9160	0.3518
0.3675	2.0158	9180	0.3524
0.3635	2.0202	9200	0.3527
0.3698	2.0246	9220	0.3520
0.3745	2.0290	9240	0.3520
0.3701	2.0334	9260	0.3519
0.3643	2.0378	9280	0.3526
0.3694	2.0422	9300	0.3524
0.3738	2.0466	9320	0.3520
0.3734	2.0509	9340	0.3522
0.3682	2.0553	9360	0.3520
0.3706	2.0597	9380	0.3521
0.3709	2.0641	9400	0.3517
0.3668	2.0685	9420	0.3518
0.3745	2.0729	9440	0.3513
0.3721	2.0773	9460	0.3526
0.3715	2.0817	9480	0.3518
0.3685	2.0861	9500	0.3516
0.3658	2.0905	9520	0.3516
0.3699	2.0949	9540	0.3515
0.3683	2.0993	9560	0.3517
0.3676	2.1037	9580	0.3521
0.3704	2.1080	9600	0.3522
0.369	2.1124	9620	0.3514
0.3697	2.1168	9640	0.3520
0.3672	2.1212	9660	0.3515
0.3697	2.1256	9680	0.3521
0.3677	2.1300	9700	0.3525
0.3679	2.1344	9720	0.3517
0.368	2.1388	9740	0.3514
0.3743	2.1432	9760	0.3517
0.3704	2.1476	9780	0.3517
0.3672	2.1520	9800	0.3515
0.3691	2.1564	9820	0.3521
0.3711	2.1608	9840	0.3513
0.3684	2.1651	9860	0.3513
0.3697	2.1695	9880	0.3523
0.3728	2.1739	9900	0.3518
0.367	2.1783	9920	0.3518
0.3682	2.1827	9940	0.3513
0.3633	2.1871	9960	0.3519
0.3709	2.1915	9980	0.3521
0.3722	2.1959	10000	0.3521
0.3606	2.2003	10020	0.3515
0.3728	2.2047	10040	0.3516
0.3684	2.2091	10060	0.3514
0.3666	2.2135	10080	0.3512
0.3677	2.2179	10100	0.3522
0.3726	2.2222	10120	0.3512
0.3673	2.2266	10140	0.3519
0.3666	2.2310	10160	0.3515
0.3674	2.2354	10180	0.3523
0.3703	2.2398	10200	0.3520
0.3656	2.2442	10220	0.3518
0.3699	2.2486	10240	0.3513
0.3742	2.2530	10260	0.3508
0.3673	2.2574	10280	0.3520
0.3719	2.2618	10300	0.3521
0.3683	2.2662	10320	0.3514
0.3671	2.2706	10340	0.3520
0.368	2.2750	10360	0.3514
0.3689	2.2793	10380	0.3514
0.3702	2.2837	10400	0.3519
0.3677	2.2881	10420	0.3521
0.3692	2.2925	10440	0.3516
0.3717	2.2969	10460	0.3509
0.3682	2.3013	10480	0.3514
0.3717	2.3057	10500	0.3509
0.37	2.3101	10520	0.3515
0.3659	2.3145	10540	0.3513
0.3688	2.3189	10560	0.3513
0.3735	2.3233	10580	0.3513
0.3709	2.3277	10600	0.3516
0.367	2.3321	10620	0.3519
0.373	2.3364	10640	0.3515
0.3682	2.3408	10660	0.3517
0.3696	2.3452	10680	0.3512
0.3684	2.3496	10700	0.3519
0.3667	2.3540	10720	0.3516
0.3714	2.3584	10740	0.3511
0.3684	2.3628	10760	0.3514
0.3634	2.3672	10780	0.3520
0.367	2.3716	10800	0.3524
0.3682	2.3760	10820	0.3517
0.366	2.3804	10840	0.3514
0.3697	2.3848	10860	0.3511
0.3644	2.3892	10880	0.3517
0.3696	2.3935	10900	0.3521
0.3637	2.3979	10920	0.3518
0.3692	2.4023	10940	0.3515
0.3682	2.4067	10960	0.3514
0.3683	2.4111	10980	0.3510
0.3681	2.4155	11000	0.3514
0.3647	2.4199	11020	0.3516
0.3679	2.4243	11040	0.3512
0.3677	2.4287	11060	0.3515
0.3636	2.4331	11080	0.3513
0.3652	2.4375	11100	0.3518
0.3668	2.4419	11120	0.3514
0.3718	2.4463	11140	0.3510
0.3666	2.4506	11160	0.3509
0.3669	2.4550	11180	0.3511
0.3685	2.4594	11200	0.3514
0.3658	2.4638	11220	0.3512
0.3675	2.4682	11240	0.3514
0.3652	2.4726	11260	0.3512
0.3661	2.4770	11280	0.3510
0.3674	2.4814	11300	0.3511
0.3685	2.4858	11320	0.3513
0.3666	2.4902	11340	0.3513
0.3706	2.4946	11360	0.3506
0.3715	2.4990	11380	0.3516
0.3714	2.5033	11400	0.3514
0.363	2.5077	11420	0.3510
0.3664	2.5121	11440	0.3513
0.3631	2.5165	11460	0.3513
0.3691	2.5209	11480	0.3515
0.3667	2.5253	11500	0.3515
0.3645	2.5297	11520	0.3513
0.364	2.5341	11540	0.3512
0.3738	2.5385	11560	0.3512
0.371	2.5429	11580	0.3515
0.369	2.5473	11600	0.3513
0.3664	2.5517	11620	0.3512
0.3675	2.5561	11640	0.3512
0.3679	2.5604	11660	0.3515
0.3684	2.5648	11680	0.3510
0.369	2.5692	11700	0.3513
0.3704	2.5736	11720	0.3515
0.368	2.5780	11740	0.3514
0.3649	2.5824	11760	0.3516
0.3724	2.5868	11780	0.3514
0.3675	2.5912	11800	0.3509
0.3674	2.5956	11820	0.3510
0.3685	2.6000	11840	0.3510
0.3721	2.6044	11860	0.3509
0.3718	2.6088	11880	0.3508
0.362	2.6132	11900	0.3513
0.3685	2.6175	11920	0.3511
0.3631	2.6219	11940	0.3512
0.3705	2.6263	11960	0.3511
0.3636	2.6307	11980	0.3513
0.37	2.6351	12000	0.3514
0.3642	2.6395	12020	0.3520
0.3655	2.6439	12040	0.3513
0.3672	2.6483	12060	0.3507
0.3665	2.6527	12080	0.3510
0.3698	2.6571	12100	0.3511
0.3647	2.6615	12120	0.3511
0.3706	2.6659	12140	0.3505
0.3644	2.6703	12160	0.3511
0.3715	2.6746	12180	0.3510
0.366	2.6790	12200	0.3512
0.3618	2.6834	12220	0.3509
0.3649	2.6878	12240	0.3510
0.372	2.6922	12260	0.3517
0.3686	2.6966	12280	0.3514
0.3653	2.7010	12300	0.3513
0.3658	2.7054	12320	0.3514
0.3672	2.7098	12340	0.3511
0.3672	2.7142	12360	0.3514
0.3691	2.7186	12380	0.3511
0.3697	2.7230	12400	0.3511
0.3682	2.7274	12420	0.3511
0.3686	2.7317	12440	0.3510
0.3658	2.7361	12460	0.3509
0.3688	2.7405	12480	0.3510
0.3669	2.7449	12500	0.3509
0.3619	2.7493	12520	0.3511
0.3659	2.7537	12540	0.3514
0.3623	2.7581	12560	0.3514
0.3674	2.7625	12580	0.3512
0.3687	2.7669	12600	0.3512
0.3653	2.7713	12620	0.3511
0.3667	2.7757	12640	0.3510
0.3648	2.7801	12660	0.3513
0.3718	2.7845	12680	0.3512
0.3684	2.7888	12700	0.3509
0.3669	2.7932	12720	0.3514
0.3697	2.7976	12740	0.3509
0.3706	2.8020	12760	0.3509
0.3737	2.8064	12780	0.3514
0.3681	2.8108	12800	0.3511
0.3677	2.8152	12820	0.3512
0.3681	2.8196	12840	0.3508
0.3732	2.8240	12860	0.3510
0.3663	2.8284	12880	0.3509
0.3674	2.8328	12900	0.3507
0.3689	2.8372	12920	0.3507
0.3699	2.8416	12940	0.3512
0.368	2.8459	12960	0.3509
0.3636	2.8503	12980	0.3514
0.3659	2.8547	13000	0.3511
0.3689	2.8591	13020	0.3514
0.3694	2.8635	13040	0.3509
0.3637	2.8679	13060	0.3510
0.3653	2.8723	13080	0.3507
0.3637	2.8767	13100	0.3510
0.3692	2.8811	13120	0.3505
0.3706	2.8855	13140	0.3515
0.3665	2.8899	13160	0.3507
0.3695	2.8943	13180	0.3508
0.3632	2.8986	13200	0.3511
0.3667	2.9030	13220	0.3507
0.3627	2.9074	13240	0.3511
0.3678	2.9118	13260	0.3514
0.3658	2.9162	13280	0.3507
0.3671	2.9206	13300	0.3514
0.3699	2.9250	13320	0.3509
0.3707	2.9294	13340	0.3507
0.3658	2.9338	13360	0.3515
0.3614	2.9382	13380	0.3511
0.3721	2.9426	13400	0.3509
0.3678	2.9470	13420	0.3509
0.372	2.9514	13440	0.3509
0.3667	2.9557	13460	0.3507
0.3651	2.9601	13480	0.3514
0.3693	2.9645	13500	0.3512
0.3664	2.9689	13520	0.3509
0.3674	2.9733	13540	0.3514
0.3706	2.9777	13560	0.3509
0.3653	2.9821	13580	0.3508
0.3699	2.9865	13600	0.3513
0.3663	2.9909	13620	0.3509
0.3646	2.9953	13640	0.3505

Framework versions

• PEFT 0.15.1
• Transformers 4.51.3
• Pytorch 2.6.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.1