Gayathri142214002's picture
update model card README.md
51443dc
|
raw
history blame
20.2 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: t5-end2end-questions-generation_3
    results: []

t5-end2end-questions-generation_3

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3421

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 7

Training results

Training Loss Epoch Step Validation Loss
2.4349 0.02 10 1.7161
1.7218 0.04 20 1.2939
1.5305 0.06 30 1.0380
1.1108 0.08 40 0.8948
1.0712 0.09 50 0.7878
0.939 0.11 60 0.7081
0.8184 0.13 70 0.6778
0.7966 0.15 80 0.6776
0.765 0.17 90 0.6301
0.6124 0.19 100 0.5941
0.6417 0.21 110 0.5919
0.6934 0.23 120 0.5772
0.6427 0.24 130 0.5463
0.6064 0.26 140 0.5295
0.6152 0.28 150 0.5302
0.5896 0.3 160 0.5361
0.6301 0.32 170 0.5405
0.563 0.34 180 0.5193
0.5129 0.36 190 0.5242
0.5303 0.38 200 0.5198
0.5461 0.39 210 0.5311
0.5553 0.41 220 0.5219
0.5699 0.43 230 0.5079
0.5846 0.45 240 0.4744
0.4582 0.47 250 0.4608
0.4997 0.49 260 0.4582
0.4826 0.51 270 0.4629
0.5534 0.53 280 0.4845
0.4457 0.54 290 0.4842
0.5113 0.56 300 0.4844
0.5168 0.58 310 0.4942
0.4885 0.6 320 0.5091
0.5165 0.62 330 0.4980
0.5986 0.64 340 0.4869
0.5048 0.66 350 0.4775
0.4521 0.68 360 0.4740
0.5259 0.69 370 0.4634
0.4904 0.71 380 0.4575
0.4734 0.73 390 0.4448
0.449 0.75 400 0.4375
0.435 0.77 410 0.4237
0.4791 0.79 420 0.4295
0.4588 0.81 430 0.4318
0.5415 0.83 440 0.4115
0.4639 0.85 450 0.4060
0.4976 0.86 460 0.4092
0.4412 0.88 470 0.4115
0.4465 0.9 480 0.4272
0.53 0.92 490 0.4298
0.4359 0.94 500 0.4297
0.4071 0.96 510 0.4356
0.463 0.98 520 0.4465
0.5354 1.0 530 0.4133
0.448 1.01 540 0.4079
0.4019 1.03 550 0.4122
0.4335 1.05 560 0.4000
0.3879 1.07 570 0.3944
0.4275 1.09 580 0.4044
0.4506 1.11 590 0.4125
0.3932 1.13 600 0.4000
0.4415 1.15 610 0.4032
0.3917 1.16 620 0.4087
0.4292 1.18 630 0.4105
0.459 1.2 640 0.4092
0.3774 1.22 650 0.4103
0.3645 1.24 660 0.4071
0.3961 1.26 670 0.4032
0.4685 1.28 680 0.4161
0.4267 1.3 690 0.4157
0.416 1.31 700 0.4039
0.4514 1.33 710 0.4065
0.3793 1.35 720 0.4084
0.4009 1.37 730 0.4018
0.4411 1.39 740 0.4060
0.4498 1.41 750 0.4203
0.3846 1.43 760 0.4247
0.4194 1.45 770 0.4192
0.3542 1.46 780 0.4225
0.4442 1.48 790 0.4174
0.4338 1.5 800 0.4042
0.3626 1.52 810 0.4054
0.4171 1.54 820 0.4104
0.366 1.56 830 0.4074
0.3463 1.58 840 0.3939
0.4783 1.6 850 0.3854
0.4476 1.62 860 0.3859
0.4233 1.63 870 0.4041
0.4241 1.65 880 0.4253
0.3957 1.67 890 0.4263
0.4751 1.69 900 0.4105
0.4266 1.71 910 0.4023
0.3685 1.73 920 0.4026
0.4025 1.75 930 0.3939
0.4099 1.77 940 0.3872
0.4008 1.78 950 0.3813
0.3646 1.8 960 0.3872
0.4462 1.82 970 0.3894
0.3752 1.84 980 0.3824
0.478 1.86 990 0.3782
0.4349 1.88 1000 0.3748
0.3901 1.9 1010 0.3754
0.4174 1.92 1020 0.3828
0.4288 1.93 1030 0.3859
0.4043 1.95 1040 0.3789
0.3998 1.97 1050 0.3839
0.424 1.99 1060 0.3940
0.383 2.01 1070 0.3959
0.3123 2.03 1080 0.3920
0.3998 2.05 1090 0.3883
0.4041 2.07 1100 0.3905
0.3889 2.08 1110 0.3844
0.4058 2.1 1120 0.3797
0.3543 2.12 1130 0.3837
0.3717 2.14 1140 0.3904
0.3966 2.16 1150 0.3824
0.3744 2.18 1160 0.3759
0.331 2.2 1170 0.3772
0.3582 2.22 1180 0.3756
0.3639 2.23 1190 0.3782
0.4402 2.25 1200 0.3825
0.3617 2.27 1210 0.3843
0.3748 2.29 1220 0.3897
0.3651 2.31 1230 0.3875
0.3694 2.33 1240 0.3842
0.4077 2.35 1250 0.3844
0.4 2.37 1260 0.3929
0.3299 2.38 1270 0.3984
0.3511 2.4 1280 0.3991
0.4368 2.42 1290 0.3872
0.4289 2.44 1300 0.3822
0.3744 2.46 1310 0.3815
0.3531 2.48 1320 0.3864
0.3567 2.5 1330 0.3910
0.4227 2.52 1340 0.3956
0.3903 2.54 1350 0.3963
0.3924 2.55 1360 0.3879
0.3678 2.57 1370 0.3809
0.3311 2.59 1380 0.3825
0.3791 2.61 1390 0.3843
0.3399 2.63 1400 0.3778
0.3797 2.65 1410 0.3762
0.357 2.67 1420 0.3689
0.3713 2.69 1430 0.3724
0.4323 2.7 1440 0.3760
0.3695 2.72 1450 0.3782
0.3662 2.74 1460 0.3764
0.3835 2.76 1470 0.3815
0.3748 2.78 1480 0.3880
0.4334 2.8 1490 0.3935
0.3937 2.82 1500 0.3935
0.3863 2.84 1510 0.3840
0.398 2.85 1520 0.3850
0.4008 2.87 1530 0.3850
0.4114 2.89 1540 0.3848
0.4229 2.91 1550 0.3807
0.3742 2.93 1560 0.3765
0.3563 2.95 1570 0.3776
0.3984 2.97 1580 0.3738
0.3757 2.99 1590 0.3757
0.3972 3.0 1600 0.3756
0.3504 3.02 1610 0.3762
0.3342 3.04 1620 0.3753
0.3545 3.06 1630 0.3686
0.3437 3.08 1640 0.3676
0.3405 3.1 1650 0.3715
0.3857 3.12 1660 0.3795
0.3641 3.14 1670 0.3848
0.3332 3.15 1680 0.3840
0.3677 3.17 1690 0.3816
0.3663 3.19 1700 0.3796
0.3522 3.21 1710 0.3754
0.3337 3.23 1720 0.3710
0.3983 3.25 1730 0.3677
0.3531 3.27 1740 0.3675
0.343 3.29 1750 0.3702
0.3892 3.31 1760 0.3723
0.3398 3.32 1770 0.3779
0.3424 3.34 1780 0.3719
0.3609 3.36 1790 0.3732
0.3777 3.38 1800 0.3705
0.3841 3.4 1810 0.3713
0.3483 3.42 1820 0.3689
0.3943 3.44 1830 0.3682
0.347 3.46 1840 0.3678
0.3237 3.47 1850 0.3670
0.3136 3.49 1860 0.3604
0.384 3.51 1870 0.3551
0.3938 3.53 1880 0.3546
0.3404 3.55 1890 0.3593
0.3441 3.57 1900 0.3561
0.3439 3.59 1910 0.3601
0.3607 3.61 1920 0.3615
0.3428 3.62 1930 0.3614
0.3889 3.64 1940 0.3604
0.4003 3.66 1950 0.3589
0.3373 3.68 1960 0.3580
0.4362 3.7 1970 0.3594
0.4004 3.72 1980 0.3633
0.369 3.74 1990 0.3641
0.3504 3.76 2000 0.3594
0.3297 3.77 2010 0.3572
0.4089 3.79 2020 0.3573
0.3714 3.81 2030 0.3549
0.2995 3.83 2040 0.3544
0.342 3.85 2050 0.3493
0.3506 3.87 2060 0.3486
0.3223 3.89 2070 0.3491
0.362 3.91 2080 0.3509
0.3544 3.92 2090 0.3512
0.3117 3.94 2100 0.3530
0.3688 3.96 2110 0.3550
0.3243 3.98 2120 0.3592
0.3384 4.0 2130 0.3632
0.3414 4.02 2140 0.3642
0.304 4.04 2150 0.3632
0.3341 4.06 2160 0.3630
0.3615 4.08 2170 0.3661
0.3405 4.09 2180 0.3673
0.3409 4.11 2190 0.3701
0.3339 4.13 2200 0.3747
0.3522 4.15 2210 0.3746
0.3435 4.17 2220 0.3732
0.3407 4.19 2230 0.3761
0.3562 4.21 2240 0.3820
0.3512 4.23 2250 0.3842
0.3887 4.24 2260 0.3821
0.3143 4.26 2270 0.3811
0.3548 4.28 2280 0.3805
0.3372 4.3 2290 0.3752
0.3452 4.32 2300 0.3692
0.3596 4.34 2310 0.3683
0.3533 4.36 2320 0.3693
0.3158 4.38 2330 0.3708
0.348 4.39 2340 0.3728
0.3255 4.41 2350 0.3720
0.3791 4.43 2360 0.3671
0.3093 4.45 2370 0.3640
0.3338 4.47 2380 0.3616
0.3637 4.49 2390 0.3599
0.3192 4.51 2400 0.3594
0.3264 4.53 2410 0.3603
0.3337 4.54 2420 0.3607
0.3146 4.56 2430 0.3607
0.3573 4.58 2440 0.3624
0.3368 4.6 2450 0.3617
0.3174 4.62 2460 0.3613
0.3245 4.64 2470 0.3630
0.355 4.66 2480 0.3619
0.3731 4.68 2490 0.3637
0.3409 4.69 2500 0.3651
0.3393 4.71 2510 0.3657
0.3461 4.73 2520 0.3665
0.3353 4.75 2530 0.3693
0.3623 4.77 2540 0.3685
0.34 4.79 2550 0.3658
0.3886 4.81 2560 0.3635
0.3454 4.83 2570 0.3628
0.3626 4.85 2580 0.3604
0.3141 4.86 2590 0.3565
0.342 4.88 2600 0.3539
0.3384 4.9 2610 0.3535
0.3603 4.92 2620 0.3527
0.3148 4.94 2630 0.3534
0.343 4.96 2640 0.3511
0.3086 4.98 2650 0.3469
0.3228 5.0 2660 0.3433
0.3563 5.01 2670 0.3426
0.3121 5.03 2680 0.3442
0.2915 5.05 2690 0.3450
0.3166 5.07 2700 0.3447
0.3298 5.09 2710 0.3444
0.3227 5.11 2720 0.3467
0.3349 5.13 2730 0.3474
0.3613 5.15 2740 0.3487
0.3352 5.16 2750 0.3506
0.294 5.18 2760 0.3507
0.3205 5.2 2770 0.3509
0.3298 5.22 2780 0.3478
0.3644 5.24 2790 0.3450
0.3233 5.26 2800 0.3440
0.3329 5.28 2810 0.3455
0.3583 5.3 2820 0.3472
0.3272 5.31 2830 0.3502
0.3069 5.33 2840 0.3520
0.322 5.35 2850 0.3550
0.3416 5.37 2860 0.3557
0.3591 5.39 2870 0.3549
0.3028 5.41 2880 0.3532
0.3471 5.43 2890 0.3519
0.3225 5.45 2900 0.3528
0.3534 5.46 2910 0.3515
0.3278 5.48 2920 0.3510
0.3368 5.5 2930 0.3509
0.3475 5.52 2940 0.3494
0.3108 5.54 2950 0.3484
0.3303 5.56 2960 0.3461
0.3206 5.58 2970 0.3459
0.3507 5.6 2980 0.3451
0.2991 5.62 2990 0.3462
0.3702 5.63 3000 0.3479
0.3358 5.65 3010 0.3481
0.3543 5.67 3020 0.3469
0.3339 5.69 3030 0.3462
0.3659 5.71 3040 0.3448
0.3024 5.73 3050 0.3441
0.3197 5.75 3060 0.3447
0.2959 5.77 3070 0.3457
0.3181 5.78 3080 0.3456
0.3318 5.8 3090 0.3463
0.3259 5.82 3100 0.3477
0.3436 5.84 3110 0.3457
0.3427 5.86 3120 0.3451
0.3428 5.88 3130 0.3443
0.3297 5.9 3140 0.3432
0.3096 5.92 3150 0.3429
0.3073 5.93 3160 0.3429
0.3108 5.95 3170 0.3435
0.3649 5.97 3180 0.3434
0.3463 5.99 3190 0.3447
0.3157 6.01 3200 0.3456
0.3055 6.03 3210 0.3467
0.3114 6.05 3220 0.3465
0.3378 6.07 3230 0.3462
0.3228 6.08 3240 0.3471
0.3415 6.1 3250 0.3472
0.3234 6.12 3260 0.3474
0.3488 6.14 3270 0.3478
0.3176 6.16 3280 0.3477
0.3189 6.18 3290 0.3467
0.3121 6.2 3300 0.3468
0.3263 6.22 3310 0.3472
0.3349 6.23 3320 0.3475
0.3238 6.25 3330 0.3472
0.3067 6.27 3340 0.3470
0.3195 6.29 3350 0.3461
0.3036 6.31 3360 0.3462
0.3012 6.33 3370 0.3454
0.3371 6.35 3380 0.3446
0.3171 6.37 3390 0.3441
0.3048 6.38 3400 0.3435
0.3604 6.4 3410 0.3434
0.2926 6.42 3420 0.3431
0.3374 6.44 3430 0.3430
0.3289 6.46 3440 0.3426
0.3356 6.48 3450 0.3420
0.3154 6.5 3460 0.3421
0.3321 6.52 3470 0.3420
0.2968 6.54 3480 0.3411
0.334 6.55 3490 0.3406
0.3393 6.57 3500 0.3403
0.3343 6.59 3510 0.3402
0.3198 6.61 3520 0.3402
0.3098 6.63 3530 0.3405
0.3059 6.65 3540 0.3407
0.3167 6.67 3550 0.3409
0.3502 6.69 3560 0.3412
0.322 6.7 3570 0.3416
0.2869 6.72 3580 0.3416
0.3067 6.74 3590 0.3418
0.3531 6.76 3600 0.3418
0.3521 6.78 3610 0.3418
0.3058 6.8 3620 0.3417
0.3179 6.82 3630 0.3420
0.3387 6.84 3640 0.3420
0.3091 6.85 3650 0.3420
0.2982 6.87 3660 0.3421
0.3131 6.89 3670 0.3422
0.303 6.91 3680 0.3421
0.3524 6.93 3690 0.3421
0.3487 6.95 3700 0.3421
0.3225 6.97 3710 0.3421
0.3379 6.99 3720 0.3421

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3