Hugging Face's logo

Lancelot53
/
flan-t5-base-xlsum

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
flan-t5-base-xlsum / README.md
Lancelot53's picture
Lancelot53
update model card README.md
bef3705
preview code
|
raw
history blame
6.79 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - xlsum
model-index:
  - name: flan-t5-base-xlsum
    results: []

flan-t5-base-xlsum

This model was trained from scratch on the xlsum dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4057

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: 6
  • eval_batch_size: 12
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
0.4372 0.05 100 0.3986
0.4257 0.09 200 0.3988
0.3988 0.14 300 0.4002
0.4148 0.18 400 0.4011
0.4156 0.23 500 0.4010
0.4102 0.28 600 0.4012
0.4198 0.32 700 0.4014
0.4085 0.37 800 0.4013
0.4199 0.42 900 0.4014
0.4143 0.46 1000 0.4008
0.4176 0.51 1100 0.4003
0.4188 0.55 1200 0.4007
0.4151 0.6 1300 0.4005
0.4221 0.65 1400 0.3990
0.416 0.69 1500 0.4004
0.4093 0.74 1600 0.3992
0.4111 0.79 1700 0.3995
0.4214 0.83 1800 0.3997
0.4061 0.88 1900 0.3998
0.4307 0.92 2000 0.3999
0.4301 0.97 2100 0.3994
0.4049 1.02 2200 0.4006
0.386 1.06 2300 0.4008
0.3948 1.11 2400 0.4015
0.3909 1.16 2500 0.4013
0.3852 1.2 2600 0.4005
0.3927 1.25 2700 0.4011
0.3973 1.29 2800 0.4021
0.3895 1.34 2900 0.4014
0.386 1.39 3000 0.4006
0.4033 1.43 3100 0.4013
0.3931 1.48 3200 0.4009
0.4035 1.53 3300 0.4003
0.4073 1.57 3400 0.4003
0.3914 1.62 3500 0.4001
0.3875 1.66 3600 0.4007
0.4051 1.71 3700 0.4007
0.3878 1.76 3800 0.4016
0.3891 1.8 3900 0.4005
0.3916 1.85 4000 0.4014
0.4147 1.9 4100 0.3999
0.4037 1.94 4200 0.3994
0.4137 1.99 4300 0.3992
0.3811 2.03 4400 0.4028
0.3702 2.08 4500 0.4030
0.3607 2.13 4600 0.4031
0.3705 2.17 4700 0.4030
0.3771 2.22 4800 0.4030
0.3643 2.27 4900 0.4026
0.3933 2.31 5000 0.4030
0.3948 2.36 5100 0.4024
0.3772 2.4 5200 0.4023
0.3791 2.45 5300 0.4036
0.3705 2.5 5400 0.4036
0.3806 2.54 5500 0.4035
0.377 2.59 5600 0.4026
0.3768 2.64 5700 0.4020
0.3765 2.68 5800 0.4031
0.3819 2.73 5900 0.4029
0.3715 2.77 6000 0.4022
0.3808 2.82 6100 0.4014
0.3905 2.87 6200 0.4016
0.3905 2.91 6300 0.4018
0.3798 2.96 6400 0.4007
0.3705 3.01 6500 0.4013
0.376 3.05 6600 0.4042
0.3599 3.1 6700 0.4048
0.3642 3.14 6800 0.4044
0.368 3.19 6900 0.4055
0.3709 3.24 7000 0.4051
0.3594 3.28 7100 0.4046
0.3723 3.33 7200 0.4045
0.3564 3.37 7300 0.4051
0.3695 3.42 7400 0.4040
0.354 3.47 7500 0.4038
0.3695 3.51 7600 0.4040
0.3769 3.56 7700 0.4040
0.361 3.61 7800 0.4044
0.3727 3.65 7900 0.4035
0.3591 3.7 8000 0.4042
0.3695 3.74 8100 0.4036
0.3747 3.79 8200 0.4043
0.3562 3.84 8300 0.4038
0.3512 3.88 8400 0.4037
0.3647 3.93 8500 0.4038
0.3657 3.98 8600 0.4041
0.3534 4.02 8700 0.4042
0.3517 4.07 8800 0.4052
0.3483 4.11 8900 0.4052
0.3514 4.16 9000 0.4056
0.3544 4.21 9100 0.4056
0.3599 4.25 9200 0.4054
0.3559 4.3 9300 0.4056
0.3738 4.35 9400 0.4056
0.3572 4.39 9500 0.4056
0.3444 4.44 9600 0.4056
0.3555 4.48 9700 0.4058
0.3583 4.53 9800 0.4059
0.3746 4.58 9900 0.4057
0.3496 4.62 10000 0.4059
0.3625 4.67 10100 0.4059
0.3529 4.72 10200 0.4058
0.3584 4.76 10300 0.4055
0.3503 4.81 10400 0.4056
0.3681 4.85 10500 0.4057
0.3542 4.9 10600 0.4057
0.3539 4.95 10700 0.4057
0.3591 4.99 10800 0.4057

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3