|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: reversemult_lr5e-4_batch128_train1-5_eval6 |
|
|
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. --> |
|
|
|
|
|
# reversemult_lr5e-4_batch128_train1-5_eval6 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.3785 |
|
|
- Accuracy: 0.0057 |
|
|
|
|
|
## 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: 0.0005 |
|
|
- train_batch_size: 128 |
|
|
- eval_batch_size: 512 |
|
|
- seed: 23452399 |
|
|
- 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 | 2.7162 | 0.0 | |
|
|
| 2.0296 | 0.0064 | 100 | 2.2743 | 0.0 | |
|
|
| 1.9424 | 0.0128 | 200 | 2.1654 | 0.0 | |
|
|
| 1.8836 | 0.0192 | 300 | 2.1261 | 0.0 | |
|
|
| 1.9049 | 0.0256 | 400 | 2.1056 | 0.0 | |
|
|
| 1.9108 | 0.032 | 500 | 2.1286 | 0.0 | |
|
|
| 1.7908 | 0.0384 | 600 | 2.0182 | 0.0 | |
|
|
| 1.6969 | 0.0448 | 700 | 1.9827 | 0.0 | |
|
|
| 1.6781 | 0.0512 | 800 | 1.9602 | 0.0 | |
|
|
| 1.575 | 0.0576 | 900 | 1.8370 | 0.0 | |
|
|
| 1.5587 | 0.064 | 1000 | 1.8525 | 0.0 | |
|
|
| 1.4983 | 0.0704 | 1100 | 1.9120 | 0.0 | |
|
|
| 1.5011 | 0.0768 | 1200 | 1.8729 | 0.0 | |
|
|
| 1.3519 | 0.0832 | 1300 | 1.8656 | 0.0 | |
|
|
| 1.4149 | 0.0896 | 1400 | 1.8366 | 0.0 | |
|
|
| 1.3179 | 0.096 | 1500 | 1.8383 | 0.0 | |
|
|
| 1.3261 | 0.1024 | 1600 | 1.7095 | 0.0 | |
|
|
| 1.4272 | 0.1088 | 1700 | 1.7269 | 0.0 | |
|
|
| 1.3181 | 0.1152 | 1800 | 1.8021 | 0.0 | |
|
|
| 1.3017 | 0.1216 | 1900 | 1.6781 | 0.0 | |
|
|
| 1.2954 | 0.128 | 2000 | 1.7248 | 0.0001 | |
|
|
| 1.3762 | 0.1344 | 2100 | 2.1858 | 0.0 | |
|
|
| 1.2999 | 0.1408 | 2200 | 1.6783 | 0.0 | |
|
|
| 1.2738 | 0.1472 | 2300 | 1.6780 | 0.0 | |
|
|
| 1.2304 | 0.1536 | 2400 | 1.7079 | 0.0 | |
|
|
| 1.2072 | 0.16 | 2500 | 1.6358 | 0.0001 | |
|
|
| 1.2027 | 0.1664 | 2600 | 1.6389 | 0.0001 | |
|
|
| 1.1565 | 0.1728 | 2700 | 1.7008 | 0.0 | |
|
|
| 1.1693 | 0.1792 | 2800 | 1.5942 | 0.0 | |
|
|
| 1.2066 | 0.1856 | 2900 | 1.6068 | 0.0001 | |
|
|
| 1.2295 | 0.192 | 3000 | 1.6025 | 0.0 | |
|
|
| 1.0896 | 0.1984 | 3100 | 1.7089 | 0.0 | |
|
|
| 1.1147 | 0.2048 | 3200 | 1.5786 | 0.0 | |
|
|
| 1.1365 | 0.2112 | 3300 | 1.5354 | 0.0001 | |
|
|
| 1.1456 | 0.2176 | 3400 | 1.5794 | 0.0001 | |
|
|
| 1.1195 | 0.224 | 3500 | 1.5774 | 0.0003 | |
|
|
| 1.1497 | 0.2304 | 3600 | 1.5569 | 0.0002 | |
|
|
| 1.1463 | 0.2368 | 3700 | 1.6149 | 0.0002 | |
|
|
| 1.1166 | 0.2432 | 3800 | 1.5591 | 0.0003 | |
|
|
| 1.1374 | 0.2496 | 3900 | 1.5637 | 0.0 | |
|
|
| 1.0243 | 0.256 | 4000 | 1.5328 | 0.0001 | |
|
|
| 1.0935 | 0.2624 | 4100 | 1.5287 | 0.0003 | |
|
|
| 1.0762 | 0.2688 | 4200 | 1.6777 | 0.0 | |
|
|
| 1.0035 | 0.2752 | 4300 | 1.5196 | 0.0 | |
|
|
| 1.0817 | 0.2816 | 4400 | 1.4903 | 0.0004 | |
|
|
| 1.0418 | 0.288 | 4500 | 1.5294 | 0.0004 | |
|
|
| 1.0771 | 0.2944 | 4600 | 1.5187 | 0.0 | |
|
|
| 1.0407 | 0.3008 | 4700 | 1.4713 | 0.0003 | |
|
|
| 0.9874 | 0.3072 | 4800 | 1.5375 | 0.0002 | |
|
|
| 0.9553 | 0.3136 | 4900 | 1.4886 | 0.0 | |
|
|
| 1.0734 | 0.32 | 5000 | 1.5172 | 0.0001 | |
|
|
| 1.012 | 0.3264 | 5100 | 1.8822 | 0.0002 | |
|
|
| 1.0574 | 0.3328 | 5200 | 1.5566 | 0.0003 | |
|
|
| 0.9948 | 0.3392 | 5300 | 1.5942 | 0.0001 | |
|
|
| 0.9474 | 0.3456 | 5400 | 1.5320 | 0.0004 | |
|
|
| 1.0058 | 0.352 | 5500 | 1.4921 | 0.0002 | |
|
|
| 1.0294 | 0.3584 | 5600 | 1.4531 | 0.0003 | |
|
|
| 0.994 | 0.3648 | 5700 | 1.4253 | 0.0005 | |
|
|
| 0.948 | 0.3712 | 5800 | 1.4519 | 0.0003 | |
|
|
| 0.9582 | 0.3776 | 5900 | 1.5040 | 0.0001 | |
|
|
| 0.9616 | 0.384 | 6000 | 1.5861 | 0.0003 | |
|
|
| 0.9159 | 0.3904 | 6100 | 1.5357 | 0.0001 | |
|
|
| 1.3541 | 0.3968 | 6200 | 2.4432 | 0.0003 | |
|
|
| 0.9235 | 0.4032 | 6300 | 1.4219 | 0.0001 | |
|
|
| 0.9238 | 0.4096 | 6400 | 1.4808 | 0.0002 | |
|
|
| 0.9173 | 0.416 | 6500 | 1.4324 | 0.0002 | |
|
|
| 0.9676 | 0.4224 | 6600 | 1.4826 | 0.0006 | |
|
|
| 0.9566 | 0.4288 | 6700 | 1.4554 | 0.0006 | |
|
|
| 0.9793 | 0.4352 | 6800 | 1.4212 | 0.0005 | |
|
|
| 0.8629 | 0.4416 | 6900 | 1.4216 | 0.0008 | |
|
|
| 0.9797 | 0.448 | 7000 | 1.4925 | 0.0003 | |
|
|
| 0.8934 | 0.4544 | 7100 | 1.4106 | 0.0002 | |
|
|
| 0.8281 | 0.4608 | 7200 | 1.4818 | 0.0005 | |
|
|
| 0.8121 | 0.4672 | 7300 | 1.4050 | 0.0003 | |
|
|
| 0.918 | 0.4736 | 7400 | 1.4581 | 0.0001 | |
|
|
| 0.9087 | 0.48 | 7500 | 1.4456 | 0.0006 | |
|
|
| 0.9041 | 0.4864 | 7600 | 1.4066 | 0.0009 | |
|
|
| 0.9103 | 0.4928 | 7700 | 1.5262 | 0.0003 | |
|
|
| 0.9182 | 0.4992 | 7800 | 1.4674 | 0.0003 | |
|
|
| 0.8723 | 0.5056 | 7900 | 1.4579 | 0.0011 | |
|
|
| 0.9286 | 0.512 | 8000 | 1.4198 | 0.0006 | |
|
|
| 0.8589 | 0.5184 | 8100 | 1.5125 | 0.0009 | |
|
|
| 0.9166 | 0.5248 | 8200 | 1.6297 | 0.0007 | |
|
|
| 0.8102 | 0.5312 | 8300 | 1.4340 | 0.0008 | |
|
|
| 0.9024 | 0.5376 | 8400 | 1.4266 | 0.0006 | |
|
|
| 0.9555 | 0.544 | 8500 | 1.6161 | 0.0011 | |
|
|
| 0.9381 | 0.5504 | 8600 | 1.3833 | 0.001 | |
|
|
| 0.9002 | 0.5568 | 8700 | 1.3657 | 0.0013 | |
|
|
| 0.8971 | 0.5632 | 8800 | 1.3565 | 0.0009 | |
|
|
| 0.9168 | 0.5696 | 8900 | 1.4560 | 0.0006 | |
|
|
| 0.8877 | 0.576 | 9000 | 1.4237 | 0.0006 | |
|
|
| 0.8288 | 0.5824 | 9100 | 1.3777 | 0.0008 | |
|
|
| 0.8614 | 0.5888 | 9200 | 1.4224 | 0.0009 | |
|
|
| 0.8473 | 0.5952 | 9300 | 1.4370 | 0.0014 | |
|
|
| 0.8731 | 0.6016 | 9400 | 1.3741 | 0.0019 | |
|
|
| 0.8507 | 0.608 | 9500 | 1.5187 | 0.0015 | |
|
|
| 0.886 | 0.6144 | 9600 | 1.4337 | 0.0017 | |
|
|
| 0.8568 | 0.6208 | 9700 | 1.3741 | 0.0014 | |
|
|
| 0.8408 | 0.6272 | 9800 | 1.3511 | 0.0019 | |
|
|
| 0.8916 | 0.6336 | 9900 | 1.4063 | 0.0018 | |
|
|
| 0.8386 | 0.64 | 10000 | 1.5553 | 0.0019 | |
|
|
| 0.8904 | 0.6464 | 10100 | 1.6633 | 0.0019 | |
|
|
| 0.8123 | 0.6528 | 10200 | 1.6016 | 0.0023 | |
|
|
| 0.8604 | 0.6592 | 10300 | 1.7775 | 0.002 | |
|
|
| 0.8749 | 0.6656 | 10400 | 1.4951 | 0.0018 | |
|
|
| 0.7694 | 0.672 | 10500 | 1.3464 | 0.0021 | |
|
|
| 0.8055 | 0.6784 | 10600 | 1.3775 | 0.002 | |
|
|
| 0.7708 | 0.6848 | 10700 | 1.3526 | 0.003 | |
|
|
| 0.7416 | 0.6912 | 10800 | 1.3530 | 0.0029 | |
|
|
| 0.8231 | 0.6976 | 10900 | 1.3654 | 0.0024 | |
|
|
| 0.8569 | 0.704 | 11000 | 1.3929 | 0.0028 | |
|
|
| 0.7288 | 0.7104 | 11100 | 1.3905 | 0.0033 | |
|
|
| 0.8154 | 0.7168 | 11200 | 1.3642 | 0.0019 | |
|
|
| 0.8655 | 0.7232 | 11300 | 1.3882 | 0.0043 | |
|
|
| 0.7324 | 0.7296 | 11400 | 1.3649 | 0.0035 | |
|
|
| 0.8012 | 0.736 | 11500 | 1.3887 | 0.0035 | |
|
|
| 0.8921 | 0.7424 | 11600 | 1.3656 | 0.0043 | |
|
|
| 0.6927 | 0.7488 | 11700 | 1.4577 | 0.0038 | |
|
|
| 0.744 | 0.7552 | 11800 | 1.3978 | 0.0035 | |
|
|
| 0.7778 | 0.7616 | 11900 | 1.3377 | 0.0034 | |
|
|
| 0.8134 | 0.768 | 12000 | 1.4253 | 0.0034 | |
|
|
| 0.6796 | 0.7744 | 12100 | 1.4866 | 0.0047 | |
|
|
| 0.7849 | 0.7808 | 12200 | 1.3650 | 0.0047 | |
|
|
| 0.7053 | 0.7872 | 12300 | 1.3903 | 0.0048 | |
|
|
| 0.8106 | 0.7936 | 12400 | 1.3366 | 0.0042 | |
|
|
| 0.7565 | 0.8 | 12500 | 1.3658 | 0.0045 | |
|
|
| 0.7687 | 0.8064 | 12600 | 1.3546 | 0.0051 | |
|
|
| 0.7462 | 0.8128 | 12700 | 1.3479 | 0.0041 | |
|
|
| 0.736 | 0.8192 | 12800 | 1.3820 | 0.0051 | |
|
|
| 0.7784 | 0.8256 | 12900 | 1.3683 | 0.0044 | |
|
|
| 0.7894 | 0.832 | 13000 | 1.3749 | 0.0061 | |
|
|
| 0.7622 | 0.8384 | 13100 | 1.3578 | 0.005 | |
|
|
| 0.704 | 0.8448 | 13200 | 1.3382 | 0.0061 | |
|
|
| 0.7611 | 0.8512 | 13300 | 1.3678 | 0.0056 | |
|
|
| 0.8074 | 0.8576 | 13400 | 1.3359 | 0.0061 | |
|
|
| 0.6895 | 0.864 | 13500 | 1.4018 | 0.0056 | |
|
|
| 0.6923 | 0.8704 | 13600 | 1.4265 | 0.0059 | |
|
|
| 0.7321 | 0.8768 | 13700 | 1.4185 | 0.0059 | |
|
|
| 0.7816 | 0.8832 | 13800 | 1.5313 | 0.0056 | |
|
|
| 0.7597 | 0.8896 | 13900 | 1.5181 | 0.005 | |
|
|
| 0.7109 | 0.896 | 14000 | 1.3711 | 0.006 | |
|
|
| 0.7126 | 0.9024 | 14100 | 1.3939 | 0.0053 | |
|
|
| 0.6799 | 0.9088 | 14200 | 1.4188 | 0.0058 | |
|
|
| 0.6851 | 0.9152 | 14300 | 1.3726 | 0.0057 | |
|
|
| 0.7676 | 0.9216 | 14400 | 1.3994 | 0.0062 | |
|
|
| 0.708 | 0.928 | 14500 | 1.3767 | 0.0063 | |
|
|
| 0.6868 | 0.9344 | 14600 | 1.3946 | 0.0059 | |
|
|
| 0.7372 | 0.9408 | 14700 | 1.3951 | 0.0058 | |
|
|
| 0.7511 | 0.9472 | 14800 | 1.3648 | 0.0057 | |
|
|
| 0.73 | 0.9536 | 14900 | 1.3713 | 0.0055 | |
|
|
| 0.6819 | 0.96 | 15000 | 1.3664 | 0.0056 | |
|
|
| 0.6634 | 0.9664 | 15100 | 1.3759 | 0.0058 | |
|
|
| 0.7381 | 0.9728 | 15200 | 1.3770 | 0.0056 | |
|
|
| 0.7407 | 0.9792 | 15300 | 1.3746 | 0.006 | |
|
|
| 0.711 | 0.9856 | 15400 | 1.3769 | 0.0057 | |
|
|
| 0.7174 | 0.992 | 15500 | 1.3793 | 0.0058 | |
|
|
| 0.7529 | 0.9984 | 15600 | 1.3785 | 0.0057 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.5.1 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.1 |
|
|
|
