|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert_baseline_prompt_adherence_task3_fold3 |
|
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. --> |
|
|
|
# bert_baseline_prompt_adherence_task3_fold3 |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3771 |
|
- Qwk: 0.6625 |
|
- Mse: 0.3768 |
|
|
|
## 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: 2e-05 |
|
- 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 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:| |
|
| No log | 0.0308 | 2 | 0.9124 | 0.1718 | 0.9125 | |
|
| No log | 0.0615 | 4 | 0.7455 | 0.0287 | 0.7453 | |
|
| No log | 0.0923 | 6 | 0.6467 | 0.0088 | 0.6463 | |
|
| No log | 0.1231 | 8 | 0.6672 | 0.0 | 0.6667 | |
|
| No log | 0.1538 | 10 | 0.6616 | 0.0 | 0.6609 | |
|
| No log | 0.1846 | 12 | 0.5837 | 0.0088 | 0.5832 | |
|
| No log | 0.2154 | 14 | 0.5535 | 0.0262 | 0.5531 | |
|
| No log | 0.2462 | 16 | 0.5233 | 0.0561 | 0.5229 | |
|
| No log | 0.2769 | 18 | 0.5108 | 0.1771 | 0.5105 | |
|
| No log | 0.3077 | 20 | 0.4573 | 0.3453 | 0.4571 | |
|
| No log | 0.3385 | 22 | 0.5081 | 0.4864 | 0.5079 | |
|
| No log | 0.3692 | 24 | 0.5390 | 0.5338 | 0.5389 | |
|
| No log | 0.4 | 26 | 0.4548 | 0.6223 | 0.4548 | |
|
| No log | 0.4308 | 28 | 0.3995 | 0.5353 | 0.3996 | |
|
| No log | 0.4615 | 30 | 0.4074 | 0.3742 | 0.4074 | |
|
| No log | 0.4923 | 32 | 0.3839 | 0.4608 | 0.3840 | |
|
| No log | 0.5231 | 34 | 0.3928 | 0.6125 | 0.3927 | |
|
| No log | 0.5538 | 36 | 0.4124 | 0.6463 | 0.4124 | |
|
| No log | 0.5846 | 38 | 0.4050 | 0.6468 | 0.4049 | |
|
| No log | 0.6154 | 40 | 0.4139 | 0.6486 | 0.4138 | |
|
| No log | 0.6462 | 42 | 0.4559 | 0.6573 | 0.4557 | |
|
| No log | 0.6769 | 44 | 0.4800 | 0.6615 | 0.4797 | |
|
| No log | 0.7077 | 46 | 0.4081 | 0.6745 | 0.4078 | |
|
| No log | 0.7385 | 48 | 0.3439 | 0.6113 | 0.3437 | |
|
| No log | 0.7692 | 50 | 0.3352 | 0.5814 | 0.3350 | |
|
| No log | 0.8 | 52 | 0.3384 | 0.6342 | 0.3382 | |
|
| No log | 0.8308 | 54 | 0.3541 | 0.6410 | 0.3538 | |
|
| No log | 0.8615 | 56 | 0.3615 | 0.6559 | 0.3613 | |
|
| No log | 0.8923 | 58 | 0.3344 | 0.6134 | 0.3341 | |
|
| No log | 0.9231 | 60 | 0.3325 | 0.4886 | 0.3322 | |
|
| No log | 0.9538 | 62 | 0.3561 | 0.4117 | 0.3558 | |
|
| No log | 0.9846 | 64 | 0.3367 | 0.4607 | 0.3364 | |
|
| No log | 1.0154 | 66 | 0.3404 | 0.6022 | 0.3401 | |
|
| No log | 1.0462 | 68 | 0.3990 | 0.6917 | 0.3988 | |
|
| No log | 1.0769 | 70 | 0.4322 | 0.6917 | 0.4320 | |
|
| No log | 1.1077 | 72 | 0.3778 | 0.6922 | 0.3776 | |
|
| No log | 1.1385 | 74 | 0.3628 | 0.6898 | 0.3626 | |
|
| No log | 1.1692 | 76 | 0.3721 | 0.6845 | 0.3720 | |
|
| No log | 1.2 | 78 | 0.3366 | 0.6579 | 0.3364 | |
|
| No log | 1.2308 | 80 | 0.3374 | 0.5566 | 0.3372 | |
|
| No log | 1.2615 | 82 | 0.3337 | 0.5624 | 0.3335 | |
|
| No log | 1.2923 | 84 | 0.3409 | 0.6597 | 0.3409 | |
|
| No log | 1.3231 | 86 | 0.3663 | 0.6636 | 0.3662 | |
|
| No log | 1.3538 | 88 | 0.3446 | 0.6706 | 0.3445 | |
|
| No log | 1.3846 | 90 | 0.3212 | 0.6512 | 0.3211 | |
|
| No log | 1.4154 | 92 | 0.3136 | 0.5933 | 0.3133 | |
|
| No log | 1.4462 | 94 | 0.3179 | 0.6185 | 0.3177 | |
|
| No log | 1.4769 | 96 | 0.3758 | 0.6839 | 0.3757 | |
|
| No log | 1.5077 | 98 | 0.5241 | 0.6836 | 0.5241 | |
|
| No log | 1.5385 | 100 | 0.5995 | 0.6664 | 0.5995 | |
|
| No log | 1.5692 | 102 | 0.5563 | 0.6593 | 0.5562 | |
|
| No log | 1.6 | 104 | 0.4366 | 0.6957 | 0.4364 | |
|
| No log | 1.6308 | 106 | 0.3213 | 0.6337 | 0.3210 | |
|
| No log | 1.6615 | 108 | 0.3290 | 0.4724 | 0.3287 | |
|
| No log | 1.6923 | 110 | 0.3851 | 0.3892 | 0.3848 | |
|
| No log | 1.7231 | 112 | 0.3805 | 0.3900 | 0.3803 | |
|
| No log | 1.7538 | 114 | 0.3327 | 0.4164 | 0.3325 | |
|
| No log | 1.7846 | 116 | 0.3158 | 0.5906 | 0.3156 | |
|
| No log | 1.8154 | 118 | 0.3835 | 0.6869 | 0.3833 | |
|
| No log | 1.8462 | 120 | 0.4522 | 0.6753 | 0.4521 | |
|
| No log | 1.8769 | 122 | 0.4753 | 0.6628 | 0.4751 | |
|
| No log | 1.9077 | 124 | 0.4371 | 0.6984 | 0.4370 | |
|
| No log | 1.9385 | 126 | 0.3581 | 0.6847 | 0.3579 | |
|
| No log | 1.9692 | 128 | 0.3072 | 0.6079 | 0.3069 | |
|
| No log | 2.0 | 130 | 0.3270 | 0.5348 | 0.3268 | |
|
| No log | 2.0308 | 132 | 0.3258 | 0.5329 | 0.3256 | |
|
| No log | 2.0615 | 134 | 0.3089 | 0.6102 | 0.3087 | |
|
| No log | 2.0923 | 136 | 0.3477 | 0.6750 | 0.3476 | |
|
| No log | 2.1231 | 138 | 0.4064 | 0.7046 | 0.4062 | |
|
| No log | 2.1538 | 140 | 0.4262 | 0.6962 | 0.4261 | |
|
| No log | 2.1846 | 142 | 0.3908 | 0.6952 | 0.3906 | |
|
| No log | 2.2154 | 144 | 0.3330 | 0.6623 | 0.3328 | |
|
| No log | 2.2462 | 146 | 0.3131 | 0.6381 | 0.3128 | |
|
| No log | 2.2769 | 148 | 0.3128 | 0.6305 | 0.3125 | |
|
| No log | 2.3077 | 150 | 0.3293 | 0.6793 | 0.3290 | |
|
| No log | 2.3385 | 152 | 0.3806 | 0.6937 | 0.3804 | |
|
| No log | 2.3692 | 154 | 0.4066 | 0.6888 | 0.4063 | |
|
| No log | 2.4 | 156 | 0.3824 | 0.6886 | 0.3822 | |
|
| No log | 2.4308 | 158 | 0.3409 | 0.6787 | 0.3407 | |
|
| No log | 2.4615 | 160 | 0.3277 | 0.6617 | 0.3274 | |
|
| No log | 2.4923 | 162 | 0.3209 | 0.6513 | 0.3206 | |
|
| No log | 2.5231 | 164 | 0.3391 | 0.6721 | 0.3389 | |
|
| No log | 2.5538 | 166 | 0.3385 | 0.6658 | 0.3383 | |
|
| No log | 2.5846 | 168 | 0.3265 | 0.6456 | 0.3262 | |
|
| No log | 2.6154 | 170 | 0.3467 | 0.6676 | 0.3465 | |
|
| No log | 2.6462 | 172 | 0.3525 | 0.6630 | 0.3523 | |
|
| No log | 2.6769 | 174 | 0.3663 | 0.6788 | 0.3661 | |
|
| No log | 2.7077 | 176 | 0.3618 | 0.6531 | 0.3616 | |
|
| No log | 2.7385 | 178 | 0.3459 | 0.6490 | 0.3456 | |
|
| No log | 2.7692 | 180 | 0.3412 | 0.6499 | 0.3410 | |
|
| No log | 2.8 | 182 | 0.3426 | 0.6523 | 0.3423 | |
|
| No log | 2.8308 | 184 | 0.3582 | 0.6617 | 0.3579 | |
|
| No log | 2.8615 | 186 | 0.3813 | 0.6792 | 0.3811 | |
|
| No log | 2.8923 | 188 | 0.3595 | 0.6692 | 0.3593 | |
|
| No log | 2.9231 | 190 | 0.3422 | 0.6504 | 0.3420 | |
|
| No log | 2.9538 | 192 | 0.3372 | 0.6452 | 0.3369 | |
|
| No log | 2.9846 | 194 | 0.3354 | 0.6488 | 0.3352 | |
|
| No log | 3.0154 | 196 | 0.3502 | 0.6656 | 0.3500 | |
|
| No log | 3.0462 | 198 | 0.3952 | 0.6955 | 0.3950 | |
|
| No log | 3.0769 | 200 | 0.4005 | 0.6925 | 0.4002 | |
|
| No log | 3.1077 | 202 | 0.3568 | 0.6638 | 0.3565 | |
|
| No log | 3.1385 | 204 | 0.3335 | 0.6570 | 0.3332 | |
|
| No log | 3.1692 | 206 | 0.3357 | 0.6589 | 0.3354 | |
|
| No log | 3.2 | 208 | 0.3498 | 0.6543 | 0.3495 | |
|
| No log | 3.2308 | 210 | 0.3520 | 0.6571 | 0.3517 | |
|
| No log | 3.2615 | 212 | 0.3458 | 0.6648 | 0.3455 | |
|
| No log | 3.2923 | 214 | 0.3566 | 0.6585 | 0.3563 | |
|
| No log | 3.3231 | 216 | 0.3721 | 0.6637 | 0.3718 | |
|
| No log | 3.3538 | 218 | 0.3803 | 0.6696 | 0.3800 | |
|
| No log | 3.3846 | 220 | 0.4057 | 0.6813 | 0.4054 | |
|
| No log | 3.4154 | 222 | 0.3797 | 0.6547 | 0.3794 | |
|
| No log | 3.4462 | 224 | 0.3430 | 0.6367 | 0.3426 | |
|
| No log | 3.4769 | 226 | 0.3384 | 0.6270 | 0.3380 | |
|
| No log | 3.5077 | 228 | 0.3518 | 0.6437 | 0.3515 | |
|
| No log | 3.5385 | 230 | 0.4057 | 0.6652 | 0.4055 | |
|
| No log | 3.5692 | 232 | 0.4604 | 0.6894 | 0.4602 | |
|
| No log | 3.6 | 234 | 0.4501 | 0.6785 | 0.4500 | |
|
| No log | 3.6308 | 236 | 0.3986 | 0.6668 | 0.3984 | |
|
| No log | 3.6615 | 238 | 0.3424 | 0.6415 | 0.3421 | |
|
| No log | 3.6923 | 240 | 0.3285 | 0.6150 | 0.3282 | |
|
| No log | 3.7231 | 242 | 0.3286 | 0.6224 | 0.3284 | |
|
| No log | 3.7538 | 244 | 0.3454 | 0.6525 | 0.3452 | |
|
| No log | 3.7846 | 246 | 0.3931 | 0.6735 | 0.3929 | |
|
| No log | 3.8154 | 248 | 0.4434 | 0.6993 | 0.4432 | |
|
| No log | 3.8462 | 250 | 0.4605 | 0.6971 | 0.4603 | |
|
| No log | 3.8769 | 252 | 0.4347 | 0.7034 | 0.4345 | |
|
| No log | 3.9077 | 254 | 0.3881 | 0.6719 | 0.3878 | |
|
| No log | 3.9385 | 256 | 0.3610 | 0.6595 | 0.3607 | |
|
| No log | 3.9692 | 258 | 0.3383 | 0.6454 | 0.3379 | |
|
| No log | 4.0 | 260 | 0.3358 | 0.6465 | 0.3355 | |
|
| No log | 4.0308 | 262 | 0.3408 | 0.6436 | 0.3404 | |
|
| No log | 4.0615 | 264 | 0.3612 | 0.6574 | 0.3608 | |
|
| No log | 4.0923 | 266 | 0.3852 | 0.6775 | 0.3848 | |
|
| No log | 4.1231 | 268 | 0.4027 | 0.6797 | 0.4024 | |
|
| No log | 4.1538 | 270 | 0.4135 | 0.6806 | 0.4132 | |
|
| No log | 4.1846 | 272 | 0.4154 | 0.6832 | 0.4150 | |
|
| No log | 4.2154 | 274 | 0.3979 | 0.6772 | 0.3975 | |
|
| No log | 4.2462 | 276 | 0.3891 | 0.6731 | 0.3886 | |
|
| No log | 4.2769 | 278 | 0.3900 | 0.6731 | 0.3896 | |
|
| No log | 4.3077 | 280 | 0.3955 | 0.6793 | 0.3951 | |
|
| No log | 4.3385 | 282 | 0.3922 | 0.6732 | 0.3917 | |
|
| No log | 4.3692 | 284 | 0.3830 | 0.6616 | 0.3825 | |
|
| No log | 4.4 | 286 | 0.3763 | 0.6596 | 0.3759 | |
|
| No log | 4.4308 | 288 | 0.3708 | 0.6541 | 0.3704 | |
|
| No log | 4.4615 | 290 | 0.3686 | 0.6535 | 0.3682 | |
|
| No log | 4.4923 | 292 | 0.3660 | 0.6574 | 0.3656 | |
|
| No log | 4.5231 | 294 | 0.3766 | 0.6577 | 0.3762 | |
|
| No log | 4.5538 | 296 | 0.3833 | 0.6686 | 0.3829 | |
|
| No log | 4.5846 | 298 | 0.3868 | 0.6721 | 0.3865 | |
|
| No log | 4.6154 | 300 | 0.3959 | 0.6784 | 0.3955 | |
|
| No log | 4.6462 | 302 | 0.3951 | 0.6784 | 0.3947 | |
|
| No log | 4.6769 | 304 | 0.3995 | 0.6743 | 0.3991 | |
|
| No log | 4.7077 | 306 | 0.3976 | 0.6793 | 0.3972 | |
|
| No log | 4.7385 | 308 | 0.3961 | 0.6772 | 0.3957 | |
|
| No log | 4.7692 | 310 | 0.3891 | 0.6722 | 0.3887 | |
|
| No log | 4.8 | 312 | 0.3856 | 0.6680 | 0.3853 | |
|
| No log | 4.8308 | 314 | 0.3834 | 0.6680 | 0.3831 | |
|
| No log | 4.8615 | 316 | 0.3814 | 0.6680 | 0.3810 | |
|
| No log | 4.8923 | 318 | 0.3799 | 0.6646 | 0.3795 | |
|
| No log | 4.9231 | 320 | 0.3793 | 0.6646 | 0.3789 | |
|
| No log | 4.9538 | 322 | 0.3780 | 0.6625 | 0.3777 | |
|
| No log | 4.9846 | 324 | 0.3771 | 0.6625 | 0.3768 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
