Hugging Face's logo

simonycl
/
best_model-yelp_polarity-16-13

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
best_model-yelp_polarity-16-13 / README.md
simonycl's picture
simonycl
update model card README.md
fb362bd
preview code
|
raw
history blame
10.6 kB
metadata
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: best_model-yelp_polarity-16-13
    results: []

best_model-yelp_polarity-16-13

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

  • Loss: 0.3000
  • Accuracy: 0.9062

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: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 150

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 1 0.6990 0.5
No log 2.0 2 0.6990 0.5
No log 3.0 3 0.6990 0.5
No log 4.0 4 0.6990 0.5
No log 5.0 5 0.6990 0.5
No log 6.0 6 0.6990 0.5
No log 7.0 7 0.6989 0.5
No log 8.0 8 0.6989 0.5
No log 9.0 9 0.6989 0.5
0.7032 10.0 10 0.6989 0.5
0.7032 11.0 11 0.6989 0.5
0.7032 12.0 12 0.6988 0.5
0.7032 13.0 13 0.6988 0.5
0.7032 14.0 14 0.6988 0.5
0.7032 15.0 15 0.6987 0.5
0.7032 16.0 16 0.6987 0.5
0.7032 17.0 17 0.6986 0.5
0.7032 18.0 18 0.6986 0.5
0.7032 19.0 19 0.6985 0.5
0.708 20.0 20 0.6985 0.5
0.708 21.0 21 0.6984 0.5
0.708 22.0 22 0.6983 0.5
0.708 23.0 23 0.6983 0.5
0.708 24.0 24 0.6982 0.5
0.708 25.0 25 0.6981 0.5
0.708 26.0 26 0.6981 0.5
0.708 27.0 27 0.6980 0.5
0.708 28.0 28 0.6979 0.5
0.708 29.0 29 0.6978 0.5
0.6974 30.0 30 0.6978 0.5
0.6974 31.0 31 0.6977 0.5
0.6974 32.0 32 0.6976 0.5
0.6974 33.0 33 0.6975 0.5
0.6974 34.0 34 0.6974 0.5
0.6974 35.0 35 0.6973 0.5
0.6974 36.0 36 0.6972 0.5
0.6974 37.0 37 0.6971 0.5
0.6974 38.0 38 0.6970 0.5
0.6974 39.0 39 0.6969 0.5
0.6965 40.0 40 0.6968 0.5
0.6965 41.0 41 0.6967 0.5
0.6965 42.0 42 0.6966 0.5
0.6965 43.0 43 0.6965 0.5
0.6965 44.0 44 0.6964 0.5
0.6965 45.0 45 0.6963 0.5
0.6965 46.0 46 0.6962 0.5
0.6965 47.0 47 0.6961 0.5
0.6965 48.0 48 0.6960 0.5
0.6965 49.0 49 0.6958 0.5
0.6971 50.0 50 0.6957 0.5
0.6971 51.0 51 0.6956 0.5
0.6971 52.0 52 0.6955 0.5
0.6971 53.0 53 0.6953 0.5
0.6971 54.0 54 0.6952 0.5
0.6971 55.0 55 0.6950 0.5
0.6971 56.0 56 0.6949 0.5
0.6971 57.0 57 0.6948 0.5
0.6971 58.0 58 0.6946 0.5
0.6971 59.0 59 0.6945 0.5
0.6932 60.0 60 0.6943 0.5
0.6932 61.0 61 0.6942 0.5
0.6932 62.0 62 0.6940 0.5
0.6932 63.0 63 0.6939 0.5
0.6932 64.0 64 0.6937 0.5
0.6932 65.0 65 0.6936 0.5
0.6932 66.0 66 0.6934 0.5
0.6932 67.0 67 0.6933 0.5
0.6932 68.0 68 0.6931 0.5
0.6932 69.0 69 0.6929 0.5
0.6964 70.0 70 0.6928 0.5
0.6964 71.0 71 0.6926 0.5
0.6964 72.0 72 0.6924 0.5
0.6964 73.0 73 0.6923 0.5
0.6964 74.0 74 0.6921 0.5
0.6964 75.0 75 0.6919 0.5
0.6964 76.0 76 0.6917 0.5
0.6964 77.0 77 0.6915 0.5
0.6964 78.0 78 0.6913 0.5
0.6964 79.0 79 0.6911 0.5
0.6875 80.0 80 0.6909 0.5
0.6875 81.0 81 0.6907 0.5
0.6875 82.0 82 0.6905 0.5
0.6875 83.0 83 0.6902 0.5
0.6875 84.0 84 0.6900 0.5
0.6875 85.0 85 0.6898 0.5
0.6875 86.0 86 0.6895 0.5
0.6875 87.0 87 0.6892 0.5
0.6875 88.0 88 0.6889 0.5
0.6875 89.0 89 0.6886 0.5
0.6885 90.0 90 0.6883 0.5
0.6885 91.0 91 0.6880 0.5
0.6885 92.0 92 0.6876 0.5
0.6885 93.0 93 0.6873 0.5
0.6885 94.0 94 0.6868 0.5
0.6885 95.0 95 0.6864 0.5
0.6885 96.0 96 0.6859 0.5
0.6885 97.0 97 0.6854 0.5
0.6885 98.0 98 0.6848 0.5
0.6885 99.0 99 0.6842 0.5
0.6748 100.0 100 0.6836 0.5
0.6748 101.0 101 0.6829 0.5
0.6748 102.0 102 0.6822 0.5
0.6748 103.0 103 0.6815 0.5312
0.6748 104.0 104 0.6807 0.5312
0.6748 105.0 105 0.6798 0.5312
0.6748 106.0 106 0.6788 0.5312
0.6748 107.0 107 0.6777 0.5312
0.6748 108.0 108 0.6765 0.5312
0.6748 109.0 109 0.6752 0.5312
0.664 110.0 110 0.6738 0.5312
0.664 111.0 111 0.6722 0.5312
0.664 112.0 112 0.6705 0.5312
0.664 113.0 113 0.6686 0.5625
0.664 114.0 114 0.6666 0.5625
0.664 115.0 115 0.6645 0.5938
0.664 116.0 116 0.6622 0.5938
0.664 117.0 117 0.6595 0.5938
0.664 118.0 118 0.6566 0.5938
0.664 119.0 119 0.6533 0.5938
0.6328 120.0 120 0.6497 0.5938
0.6328 121.0 121 0.6456 0.5938
0.6328 122.0 122 0.6410 0.6562
0.6328 123.0 123 0.6359 0.6875
0.6328 124.0 124 0.6302 0.6875
0.6328 125.0 125 0.6238 0.7188
0.6328 126.0 126 0.6164 0.7188
0.6328 127.0 127 0.6080 0.7812
0.6328 128.0 128 0.5986 0.7812
0.6328 129.0 129 0.5881 0.7812
0.5516 130.0 130 0.5762 0.8125
0.5516 131.0 131 0.5633 0.875
0.5516 132.0 132 0.5493 0.875
0.5516 133.0 133 0.5349 0.875
0.5516 134.0 134 0.5201 0.875
0.5516 135.0 135 0.5055 0.875
0.5516 136.0 136 0.4909 0.875
0.5516 137.0 137 0.4762 0.875
0.5516 138.0 138 0.4608 0.875
0.5516 139.0 139 0.4448 0.875
0.3883 140.0 140 0.4275 0.9375
0.3883 141.0 141 0.4112 0.9062
0.3883 142.0 142 0.3955 0.9062
0.3883 143.0 143 0.3799 0.9062
0.3883 144.0 144 0.3660 0.9062
0.3883 145.0 145 0.3524 0.9062
0.3883 146.0 146 0.3394 0.9062
0.3883 147.0 147 0.3270 0.9062
0.3883 148.0 148 0.3159 0.9062
0.3883 149.0 149 0.3072 0.9062
0.2135 150.0 150 0.3000 0.9062

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.4.0
  • Tokenizers 0.13.3