<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
masked-sentence-generation-t5-base
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7392
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.9984 | 0.05 | 80 | 2.7041 |
2.8752 | 0.1 | 160 | 2.7021 |
2.9314 | 0.15 | 240 | 2.6966 |
2.8541 | 0.2 | 320 | 2.6968 |
2.8674 | 0.25 | 400 | 2.6900 |
2.8706 | 0.3 | 480 | 2.6886 |
2.7718 | 0.34 | 560 | 2.6908 |
2.8503 | 0.39 | 640 | 2.6877 |
2.8195 | 0.44 | 720 | 2.6902 |
2.8569 | 0.49 | 800 | 2.6893 |
2.8372 | 0.54 | 880 | 2.6859 |
2.8915 | 0.59 | 960 | 2.6898 |
2.9687 | 0.64 | 1040 | 2.6909 |
2.832 | 0.69 | 1120 | 2.6841 |
2.8425 | 0.74 | 1200 | 2.6842 |
2.8114 | 0.79 | 1280 | 2.6766 |
2.8101 | 0.84 | 1360 | 2.6783 |
2.8837 | 0.89 | 1440 | 2.6781 |
2.894 | 0.94 | 1520 | 2.6754 |
2.9183 | 0.99 | 1600 | 2.6762 |
2.6916 | 1.03 | 1680 | 2.6889 |
2.5812 | 1.08 | 1760 | 2.6896 |
2.5522 | 1.13 | 1840 | 2.6943 |
2.5368 | 1.18 | 1920 | 2.6928 |
2.5987 | 1.23 | 2000 | 2.6927 |
2.5625 | 1.28 | 2080 | 2.6899 |
2.4946 | 1.33 | 2160 | 2.6942 |
2.5902 | 1.38 | 2240 | 2.6900 |
2.5415 | 1.43 | 2320 | 2.6897 |
2.5767 | 1.48 | 2400 | 2.6858 |
2.6262 | 1.53 | 2480 | 2.6825 |
2.6066 | 1.58 | 2560 | 2.6818 |
2.5387 | 1.63 | 2640 | 2.6840 |
2.5795 | 1.67 | 2720 | 2.6828 |
2.5521 | 1.72 | 2800 | 2.6871 |
2.5477 | 1.77 | 2880 | 2.6836 |
2.587 | 1.82 | 2960 | 2.6824 |
2.529 | 1.87 | 3040 | 2.6871 |
2.6221 | 1.92 | 3120 | 2.6838 |
2.6353 | 1.97 | 3200 | 2.6803 |
2.5419 | 2.02 | 3280 | 2.6879 |
2.4521 | 2.07 | 3360 | 2.7027 |
2.3415 | 2.12 | 3440 | 2.7105 |
2.3483 | 2.17 | 3520 | 2.7140 |
2.3493 | 2.22 | 3600 | 2.7144 |
2.3967 | 2.27 | 3680 | 2.7134 |
2.3544 | 2.32 | 3760 | 2.7122 |
2.3192 | 2.36 | 3840 | 2.7175 |
2.3381 | 2.41 | 3920 | 2.7166 |
2.3667 | 2.46 | 4000 | 2.7165 |
2.3997 | 2.51 | 4080 | 2.7106 |
2.3178 | 2.56 | 4160 | 2.7154 |
2.4036 | 2.61 | 4240 | 2.7144 |
2.3797 | 2.66 | 4320 | 2.7129 |
2.3354 | 2.71 | 4400 | 2.7136 |
2.4109 | 2.76 | 4480 | 2.7118 |
2.387 | 2.81 | 4560 | 2.7097 |
2.3934 | 2.86 | 4640 | 2.7103 |
2.3956 | 2.91 | 4720 | 2.7103 |
2.4086 | 2.96 | 4800 | 2.7111 |
2.4083 | 3.0 | 4880 | 2.7110 |
2.3121 | 3.05 | 4960 | 2.7230 |
2.263 | 3.1 | 5040 | 2.7252 |
2.2722 | 3.15 | 5120 | 2.7296 |
2.2053 | 3.2 | 5200 | 2.7309 |
2.1969 | 3.25 | 5280 | 2.7363 |
2.2684 | 3.3 | 5360 | 2.7396 |
2.2789 | 3.35 | 5440 | 2.7376 |
2.2227 | 3.4 | 5520 | 2.7384 |
2.2886 | 3.45 | 5600 | 2.7390 |
2.2182 | 3.5 | 5680 | 2.7376 |
2.2738 | 3.55 | 5760 | 2.7394 |
2.1687 | 3.6 | 5840 | 2.7386 |
2.2548 | 3.65 | 5920 | 2.7371 |
2.2391 | 3.69 | 6000 | 2.7372 |
2.2031 | 3.74 | 6080 | 2.7391 |
2.1885 | 3.79 | 6160 | 2.7400 |
2.216 | 3.84 | 6240 | 2.7406 |
2.272 | 3.89 | 6320 | 2.7401 |
2.3455 | 3.94 | 6400 | 2.7395 |
2.2889 | 3.99 | 6480 | 2.7392 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.11.0