Hugging Face's logo

austin
/
medication-lists

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
medication-lists / README.md
cmcmaster's picture
cmcmaster
End of training
64da2d8
preview code
|
raw history blame
No virus
4.59 kB
metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
  - generated_from_trainer
model-index:
  - name: medication-lists
    results: []

medication-lists

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: 0.1027

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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
1.7961 0.3 50 0.7538
0.7207 0.61 100 0.3876
0.4596 0.91 150 0.2763
0.3536 1.22 200 0.2265
0.3089 1.52 250 0.1937
0.2736 1.83 300 0.1842
0.2415 2.13 350 0.1713
0.2309 2.44 400 0.1601
0.2011 2.74 450 0.1533
0.198 3.05 500 0.1464
0.1816 3.35 550 0.1418
0.1887 3.66 600 0.1354
0.1717 3.96 650 0.1295
0.1589 4.27 700 0.1320
0.1606 4.57 750 0.1230
0.1545 4.88 800 0.1255
0.1502 5.18 850 0.1247
0.1438 5.49 900 0.1251
0.1395 5.79 950 0.1222
0.1414 6.1 1000 0.1173
0.133 6.4 1050 0.1149
0.1338 6.71 1100 0.1124
0.1361 7.01 1150 0.1148
0.1269 7.32 1200 0.1137
0.123 7.62 1250 0.1145
0.1203 7.93 1300 0.1129
0.1194 8.23 1350 0.1081
0.1177 8.54 1400 0.1099
0.1173 8.84 1450 0.1109
0.113 9.15 1500 0.1107
0.1122 9.45 1550 0.1068
0.11 9.76 1600 0.1072
0.1078 10.06 1650 0.1086
0.101 10.37 1700 0.1088
0.1106 10.67 1750 0.1079
0.1094 10.98 1800 0.1109
0.1072 11.28 1850 0.1054
0.103 11.59 1900 0.1062
0.1009 11.89 1950 0.1051
0.1005 12.2 2000 0.1049
0.0985 12.5 2050 0.1059
0.0983 12.8 2100 0.1063
0.0953 13.11 2150 0.1062
0.0935 13.41 2200 0.1044
0.1003 13.72 2250 0.1034
0.0935 14.02 2300 0.1049
0.0935 14.33 2350 0.1038
0.096 14.63 2400 0.1020
0.0894 14.94 2450 0.1048
0.0931 15.24 2500 0.1034
0.0888 15.55 2550 0.1030
0.0904 15.85 2600 0.1038
0.0885 16.16 2650 0.1046
0.088 16.46 2700 0.1041
0.0925 16.77 2750 0.1027
0.0835 17.07 2800 0.1034
0.089 17.38 2850 0.1036
0.0844 17.68 2900 0.1043
0.0866 17.99 2950 0.1031
0.0835 18.29 3000 0.1030
0.0826 18.6 3050 0.1028
0.0874 18.9 3100 0.1018
0.0846 19.21 3150 0.1030
0.0852 19.51 3200 0.1026
0.0835 19.82 3250 0.1027

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.11.0
  • Tokenizers 0.14.1