|
|
--- |
|
|
library_name: transformers |
|
|
base_model: mtzig/reverse_add_replicate_eval17_corruptedfull |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: reverse_add_replicate_eval17_corruptedfull |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# reverse_add_replicate_eval17_corruptedfull |
|
|
|
|
|
This model is a fine-tuned version of [mtzig/reverse_add_replicate_eval17_corruptedfull](https://huggingface.co/mtzig/reverse_add_replicate_eval17_corruptedfull) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0001 |
|
|
- Accuracy: 0.999 |
|
|
|
|
|
## 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: 0.001 |
|
|
- train_batch_size: 128 |
|
|
- eval_batch_size: 128 |
|
|
- seed: 7658372 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:------:|:-----:|:---------------:|:--------:| |
|
|
| No log | 0 | 0 | 0.5300 | 0.0 | |
|
|
| 0.0 | 0.0064 | 100 | 0.0606 | 0.611 | |
|
|
| 0.0004 | 0.0128 | 200 | 0.1205 | 0.524 | |
|
|
| 0.0022 | 0.0192 | 300 | 0.0363 | 0.807 | |
|
|
| 0.017 | 0.0256 | 400 | 0.0068 | 0.967 | |
|
|
| 0.0207 | 0.032 | 500 | 0.0137 | 0.94 | |
|
|
| 0.0673 | 0.0384 | 600 | 0.1015 | 0.698 | |
|
|
| 0.0152 | 0.0448 | 700 | 0.0296 | 0.861 | |
|
|
| 0.0094 | 0.0512 | 800 | 0.1813 | 0.442 | |
|
|
| 0.0363 | 0.0576 | 900 | 0.1089 | 0.641 | |
|
|
| 0.0214 | 0.064 | 1000 | 0.1929 | 0.482 | |
|
|
| 0.0731 | 0.0704 | 1100 | 0.0817 | 0.726 | |
|
|
| 0.16 | 0.0768 | 1200 | 0.3241 | 0.266 | |
|
|
| 0.0086 | 0.0832 | 1300 | 0.0542 | 0.797 | |
|
|
| 0.0064 | 0.0896 | 1400 | 0.0304 | 0.887 | |
|
|
| 0.8944 | 0.096 | 1500 | 0.7904 | 0.175 | |
|
|
| 0.1341 | 0.1024 | 1600 | 0.9554 | 0.304 | |
|
|
| 2.3124 | 0.1088 | 1700 | 2.1227 | 0.002 | |
|
|
| 0.0894 | 0.1152 | 1800 | 0.4001 | 0.315 | |
|
|
| 0.0233 | 0.1216 | 1900 | 0.0531 | 0.772 | |
|
|
| 0.137 | 0.128 | 2000 | 0.4018 | 0.253 | |
|
|
| 0.0328 | 0.1344 | 2100 | 0.1418 | 0.476 | |
|
|
| 0.0368 | 0.1408 | 2200 | 0.1911 | 0.524 | |
|
|
| 0.3687 | 0.1472 | 2300 | 0.4512 | 0.258 | |
|
|
| 0.0715 | 0.1536 | 2400 | 0.0745 | 0.757 | |
|
|
| 0.0893 | 0.16 | 2500 | 0.5588 | 0.355 | |
|
|
| 0.0093 | 0.1664 | 2600 | 0.0366 | 0.867 | |
|
|
| 0.0854 | 0.1728 | 2700 | 0.0645 | 0.764 | |
|
|
| 0.0019 | 0.1792 | 2800 | 0.1039 | 0.721 | |
|
|
| 0.0143 | 0.1856 | 2900 | 0.0732 | 0.768 | |
|
|
| 0.0019 | 0.192 | 3000 | 0.0486 | 0.75 | |
|
|
| 0.062 | 0.1984 | 3100 | 0.0598 | 0.775 | |
|
|
| 0.034 | 0.2048 | 3200 | 0.0564 | 0.769 | |
|
|
| 0.0059 | 0.2112 | 3300 | 0.0615 | 0.793 | |
|
|
| 0.0842 | 0.2176 | 3400 | 0.2345 | 0.491 | |
|
|
| 0.0288 | 0.224 | 3500 | 0.0163 | 0.92 | |
|
|
| 0.0017 | 0.2304 | 3600 | 0.0107 | 0.964 | |
|
|
| 0.0098 | 0.2368 | 3700 | 0.0104 | 0.957 | |
|
|
| 0.0013 | 0.2432 | 3800 | 0.0176 | 0.915 | |
|
|
| 0.0036 | 0.2496 | 3900 | 0.0867 | 0.789 | |
|
|
| 0.0609 | 0.256 | 4000 | 0.1206 | 0.672 | |
|
|
| 0.004 | 0.2624 | 4100 | 0.1023 | 0.712 | |
|
|
| 0.1293 | 0.2688 | 4200 | 0.5344 | 0.456 | |
|
|
| 0.0433 | 0.2752 | 4300 | 0.0458 | 0.834 | |
|
|
| 0.0042 | 0.2816 | 4400 | 0.0221 | 0.913 | |
|
|
| 0.0171 | 0.288 | 4500 | 0.0827 | 0.709 | |
|
|
| 0.0226 | 0.2944 | 4600 | 0.4539 | 0.271 | |
|
|
| 0.0017 | 0.3008 | 4700 | 0.0143 | 0.938 | |
|
|
| 0.0007 | 0.3072 | 4800 | 0.0149 | 0.94 | |
|
|
| 0.0003 | 0.3136 | 4900 | 0.0022 | 0.994 | |
|
|
| 0.0109 | 0.32 | 5000 | 0.0412 | 0.843 | |
|
|
| 0.0036 | 0.3264 | 5100 | 0.0386 | 0.847 | |
|
|
| 0.014 | 0.3328 | 5200 | 0.0168 | 0.909 | |
|
|
| 0.0021 | 0.3392 | 5300 | 0.2362 | 0.616 | |
|
|
| 0.0221 | 0.3456 | 5400 | 0.0123 | 0.948 | |
|
|
| 0.0271 | 0.352 | 5500 | 0.0997 | 0.732 | |
|
|
| 0.0002 | 0.3584 | 5600 | 0.0598 | 0.801 | |
|
|
| 0.0302 | 0.3648 | 5700 | 1.1304 | 0.282 | |
|
|
| 0.0044 | 0.3712 | 5800 | 0.1238 | 0.702 | |
|
|
| 0.0006 | 0.3776 | 5900 | 0.1477 | 0.674 | |
|
|
| 0.0039 | 0.384 | 6000 | 0.0153 | 0.928 | |
|
|
| 0.0001 | 0.3904 | 6100 | 0.0137 | 0.943 | |
|
|
| 0.0523 | 0.3968 | 6200 | 0.1729 | 0.675 | |
|
|
| 0.0022 | 0.4032 | 6300 | 0.1563 | 0.626 | |
|
|
| 0.0008 | 0.4096 | 6400 | 0.6156 | 0.458 | |
|
|
| 0.0003 | 0.416 | 6500 | 0.0078 | 0.973 | |
|
|
| 0.0089 | 0.4224 | 6600 | 0.0030 | 0.986 | |
|
|
| 0.1903 | 0.4288 | 6700 | 0.5253 | 0.438 | |
|
|
| 0.0006 | 0.4352 | 6800 | 0.0017 | 0.995 | |
|
|
| 0.0022 | 0.4416 | 6900 | 0.0443 | 0.884 | |
|
|
| 0.0 | 0.448 | 7000 | 0.0056 | 0.979 | |
|
|
| 0.0 | 0.4544 | 7100 | 0.0015 | 0.994 | |
|
|
| 0.0004 | 0.4608 | 7200 | 0.0081 | 0.953 | |
|
|
| 0.1095 | 0.4672 | 7300 | 0.2346 | 0.519 | |
|
|
| 0.004 | 0.4736 | 7400 | 0.0062 | 0.97 | |
|
|
| 0.0021 | 0.48 | 7500 | 0.0128 | 0.942 | |
|
|
| 0.0002 | 0.4864 | 7600 | 0.0092 | 0.954 | |
|
|
| 0.0005 | 0.4928 | 7700 | 0.0590 | 0.837 | |
|
|
| 0.0009 | 0.4992 | 7800 | 0.0009 | 0.998 | |
|
|
| 0.0007 | 0.5056 | 7900 | 0.0271 | 0.915 | |
|
|
| 0.0017 | 0.512 | 8000 | 0.0130 | 0.936 | |
|
|
| 0.0004 | 0.5184 | 8100 | 0.0188 | 0.923 | |
|
|
| 0.0 | 0.5248 | 8200 | 0.0008 | 0.998 | |
|
|
| 0.0 | 0.5312 | 8300 | 0.0002 | 0.998 | |
|
|
| 0.0 | 0.5376 | 8400 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.544 | 8500 | 0.0003 | 0.998 | |
|
|
| 0.0021 | 0.5504 | 8600 | 0.1908 | 0.563 | |
|
|
| 0.0081 | 0.5568 | 8700 | 0.0226 | 0.909 | |
|
|
| 0.0012 | 0.5632 | 8800 | 0.0029 | 0.982 | |
|
|
| 0.0006 | 0.5696 | 8900 | 0.0034 | 0.987 | |
|
|
| 0.031 | 0.576 | 9000 | 0.0031 | 0.993 | |
|
|
| 0.0025 | 0.5824 | 9100 | 0.0056 | 0.974 | |
|
|
| 0.0099 | 0.5888 | 9200 | 0.2531 | 0.67 | |
|
|
| 0.0002 | 0.5952 | 9300 | 0.0039 | 0.991 | |
|
|
| 0.0003 | 0.6016 | 9400 | 0.0010 | 0.997 | |
|
|
| 0.0 | 0.608 | 9500 | 0.0001 | 1.0 | |
|
|
| 0.0 | 0.6144 | 9600 | 0.0001 | 1.0 | |
|
|
| 0.0 | 0.6208 | 9700 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6272 | 9800 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6336 | 9900 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.64 | 10000 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6464 | 10100 | 0.0001 | 1.0 | |
|
|
| 0.0 | 0.6528 | 10200 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6592 | 10300 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6656 | 10400 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.672 | 10500 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6784 | 10600 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6848 | 10700 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.6912 | 10800 | 0.0000 | 1.0 | |
|
|
| 0.0011 | 0.6976 | 10900 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.704 | 11000 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.7104 | 11100 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.7168 | 11200 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.7232 | 11300 | 0.0000 | 1.0 | |
|
|
| 0.0 | 0.7296 | 11400 | 0.0001 | 1.0 | |
|
|
| 0.0001 | 0.736 | 11500 | 0.0152 | 0.928 | |
|
|
| 0.0001 | 0.7424 | 11600 | 0.0004 | 0.998 | |
|
|
| 0.0008 | 0.7488 | 11700 | 0.0081 | 0.958 | |
|
|
| 0.0 | 0.7552 | 11800 | 0.0038 | 0.983 | |
|
|
| 0.0 | 0.7616 | 11900 | 0.0005 | 0.998 | |
|
|
| 0.0 | 0.768 | 12000 | 0.0005 | 0.999 | |
|
|
| 0.0 | 0.7744 | 12100 | 0.0004 | 0.999 | |
|
|
| 0.0 | 0.7808 | 12200 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.7872 | 12300 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.7936 | 12400 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8 | 12500 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8064 | 12600 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8128 | 12700 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8192 | 12800 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8256 | 12900 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.832 | 13000 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8384 | 13100 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8448 | 13200 | 0.0003 | 0.999 | |
|
|
| 0.0 | 0.8512 | 13300 | 0.0002 | 0.999 | |
|
|
| 0.0 | 0.8576 | 13400 | 0.0002 | 0.999 | |
|
|
| 0.0 | 0.864 | 13500 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.8704 | 13600 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.8768 | 13700 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.8832 | 13800 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.8896 | 13900 | 0.0002 | 0.999 | |
|
|
| 0.0 | 0.896 | 14000 | 0.0002 | 0.999 | |
|
|
| 0.0 | 0.9024 | 14100 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9088 | 14200 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9152 | 14300 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9216 | 14400 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.928 | 14500 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9344 | 14600 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9408 | 14700 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9472 | 14800 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9536 | 14900 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.96 | 15000 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9664 | 15100 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9728 | 15200 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9792 | 15300 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9856 | 15400 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.992 | 15500 | 0.0001 | 0.999 | |
|
|
| 0.0 | 0.9984 | 15600 | 0.0001 | 0.999 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.5.1 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.1 |
|
|
|
