|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert_baseline_language_task6_fold4 |
|
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_language_task6_fold4 |
|
|
|
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: 0.4886 |
|
- Qwk: 0.7157 |
|
- Mse: 0.4886 |
|
|
|
## 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 | 0.0294 | 2 | 2.2411 | 0.0 | 2.2411 | |
|
| No log | 0.0588 | 4 | 1.8734 | -0.0178 | 1.8734 | |
|
| No log | 0.0882 | 6 | 1.6090 | 0.0059 | 1.6090 | |
|
| No log | 0.1176 | 8 | 1.2192 | 0.0059 | 1.2192 | |
|
| No log | 0.1471 | 10 | 0.9341 | 0.0059 | 0.9341 | |
|
| No log | 0.1765 | 12 | 0.7364 | 0.1416 | 0.7364 | |
|
| No log | 0.2059 | 14 | 0.6982 | 0.2687 | 0.6982 | |
|
| No log | 0.2353 | 16 | 0.6582 | 0.3372 | 0.6582 | |
|
| No log | 0.2647 | 18 | 0.7135 | 0.1462 | 0.7135 | |
|
| No log | 0.2941 | 20 | 0.6798 | 0.2206 | 0.6798 | |
|
| No log | 0.3235 | 22 | 0.5955 | 0.3915 | 0.5955 | |
|
| No log | 0.3529 | 24 | 0.6219 | 0.3622 | 0.6219 | |
|
| No log | 0.3824 | 26 | 0.5703 | 0.3992 | 0.5703 | |
|
| No log | 0.4118 | 28 | 0.5099 | 0.4137 | 0.5099 | |
|
| No log | 0.4412 | 30 | 0.5199 | 0.4116 | 0.5199 | |
|
| No log | 0.4706 | 32 | 0.5644 | 0.4094 | 0.5644 | |
|
| No log | 0.5 | 34 | 0.5463 | 0.4109 | 0.5463 | |
|
| No log | 0.5294 | 36 | 0.4851 | 0.3907 | 0.4851 | |
|
| No log | 0.5588 | 38 | 0.4850 | 0.4156 | 0.4850 | |
|
| No log | 0.5882 | 40 | 0.5052 | 0.4150 | 0.5052 | |
|
| No log | 0.6176 | 42 | 0.4521 | 0.4313 | 0.4521 | |
|
| No log | 0.6471 | 44 | 0.4285 | 0.3921 | 0.4285 | |
|
| No log | 0.6765 | 46 | 0.4230 | 0.4170 | 0.4230 | |
|
| No log | 0.7059 | 48 | 0.4622 | 0.4317 | 0.4622 | |
|
| No log | 0.7353 | 50 | 0.5184 | 0.4332 | 0.5184 | |
|
| No log | 0.7647 | 52 | 0.5387 | 0.4339 | 0.5387 | |
|
| No log | 0.7941 | 54 | 0.5345 | 0.4536 | 0.5345 | |
|
| No log | 0.8235 | 56 | 0.4593 | 0.4674 | 0.4593 | |
|
| No log | 0.8529 | 58 | 0.4454 | 0.5019 | 0.4454 | |
|
| No log | 0.8824 | 60 | 0.5377 | 0.6217 | 0.5377 | |
|
| No log | 0.9118 | 62 | 0.7227 | 0.6473 | 0.7227 | |
|
| No log | 0.9412 | 64 | 0.6967 | 0.5892 | 0.6967 | |
|
| No log | 0.9706 | 66 | 0.4789 | 0.5329 | 0.4789 | |
|
| No log | 1.0 | 68 | 0.4475 | 0.5381 | 0.4475 | |
|
| No log | 1.0294 | 70 | 0.4883 | 0.5168 | 0.4883 | |
|
| No log | 1.0588 | 72 | 0.4881 | 0.5379 | 0.4881 | |
|
| No log | 1.0882 | 74 | 0.4513 | 0.5417 | 0.4513 | |
|
| No log | 1.1176 | 76 | 0.4886 | 0.5726 | 0.4886 | |
|
| No log | 1.1471 | 78 | 0.5485 | 0.6355 | 0.5485 | |
|
| No log | 1.1765 | 80 | 0.5511 | 0.6223 | 0.5511 | |
|
| No log | 1.2059 | 82 | 0.4701 | 0.5498 | 0.4701 | |
|
| No log | 1.2353 | 84 | 0.4336 | 0.5411 | 0.4336 | |
|
| No log | 1.2647 | 86 | 0.4810 | 0.5556 | 0.4810 | |
|
| No log | 1.2941 | 88 | 0.4668 | 0.5530 | 0.4668 | |
|
| No log | 1.3235 | 90 | 0.3993 | 0.5542 | 0.3993 | |
|
| No log | 1.3529 | 92 | 0.4006 | 0.5528 | 0.4006 | |
|
| No log | 1.3824 | 94 | 0.4392 | 0.5585 | 0.4392 | |
|
| No log | 1.4118 | 96 | 0.4205 | 0.5438 | 0.4205 | |
|
| No log | 1.4412 | 98 | 0.4390 | 0.5543 | 0.4390 | |
|
| No log | 1.4706 | 100 | 0.5557 | 0.6166 | 0.5557 | |
|
| No log | 1.5 | 102 | 0.5909 | 0.7254 | 0.5909 | |
|
| No log | 1.5294 | 104 | 0.5077 | 0.7405 | 0.5077 | |
|
| No log | 1.5588 | 106 | 0.4091 | 0.6640 | 0.4091 | |
|
| No log | 1.5882 | 108 | 0.4592 | 0.6912 | 0.4592 | |
|
| No log | 1.6176 | 110 | 0.6420 | 0.7297 | 0.6420 | |
|
| No log | 1.6471 | 112 | 0.7219 | 0.7019 | 0.7219 | |
|
| No log | 1.6765 | 114 | 0.5558 | 0.7405 | 0.5558 | |
|
| No log | 1.7059 | 116 | 0.3751 | 0.6338 | 0.3751 | |
|
| No log | 1.7353 | 118 | 0.3983 | 0.5147 | 0.3983 | |
|
| No log | 1.7647 | 120 | 0.3774 | 0.5266 | 0.3774 | |
|
| No log | 1.7941 | 122 | 0.4202 | 0.6608 | 0.4202 | |
|
| No log | 1.8235 | 124 | 0.5371 | 0.6994 | 0.5371 | |
|
| No log | 1.8529 | 126 | 0.4793 | 0.5619 | 0.4793 | |
|
| No log | 1.8824 | 128 | 0.4083 | 0.5331 | 0.4083 | |
|
| No log | 1.9118 | 130 | 0.4079 | 0.5321 | 0.4079 | |
|
| No log | 1.9412 | 132 | 0.3693 | 0.5479 | 0.3693 | |
|
| No log | 1.9706 | 134 | 0.3606 | 0.5525 | 0.3606 | |
|
| No log | 2.0 | 136 | 0.3729 | 0.5439 | 0.3729 | |
|
| No log | 2.0294 | 138 | 0.4628 | 0.5409 | 0.4628 | |
|
| No log | 2.0588 | 140 | 0.5351 | 0.6159 | 0.5351 | |
|
| No log | 2.0882 | 142 | 0.5333 | 0.6968 | 0.5333 | |
|
| No log | 2.1176 | 144 | 0.4991 | 0.7022 | 0.4991 | |
|
| No log | 2.1471 | 146 | 0.5203 | 0.7229 | 0.5203 | |
|
| No log | 2.1765 | 148 | 0.5320 | 0.7349 | 0.5320 | |
|
| No log | 2.2059 | 150 | 0.5657 | 0.7320 | 0.5657 | |
|
| No log | 2.2353 | 152 | 0.4832 | 0.7194 | 0.4832 | |
|
| No log | 2.2647 | 154 | 0.4500 | 0.7072 | 0.4500 | |
|
| No log | 2.2941 | 156 | 0.4751 | 0.7137 | 0.4751 | |
|
| No log | 2.3235 | 158 | 0.5329 | 0.7259 | 0.5329 | |
|
| No log | 2.3529 | 160 | 0.6005 | 0.7169 | 0.6005 | |
|
| No log | 2.3824 | 162 | 0.5667 | 0.7338 | 0.5667 | |
|
| No log | 2.4118 | 164 | 0.4374 | 0.7067 | 0.4374 | |
|
| No log | 2.4412 | 166 | 0.4124 | 0.6831 | 0.4124 | |
|
| No log | 2.4706 | 168 | 0.4354 | 0.6921 | 0.4354 | |
|
| No log | 2.5 | 170 | 0.4397 | 0.6839 | 0.4397 | |
|
| No log | 2.5294 | 172 | 0.4214 | 0.6446 | 0.4214 | |
|
| No log | 2.5588 | 174 | 0.4354 | 0.6473 | 0.4354 | |
|
| No log | 2.5882 | 176 | 0.4596 | 0.6485 | 0.4596 | |
|
| No log | 2.6176 | 178 | 0.4180 | 0.6243 | 0.4180 | |
|
| No log | 2.6471 | 180 | 0.4142 | 0.6336 | 0.4142 | |
|
| No log | 2.6765 | 182 | 0.3653 | 0.5950 | 0.3653 | |
|
| No log | 2.7059 | 184 | 0.3595 | 0.6087 | 0.3595 | |
|
| No log | 2.7353 | 186 | 0.3716 | 0.6402 | 0.3716 | |
|
| No log | 2.7647 | 188 | 0.4491 | 0.7032 | 0.4491 | |
|
| No log | 2.7941 | 190 | 0.4727 | 0.7077 | 0.4727 | |
|
| No log | 2.8235 | 192 | 0.4595 | 0.6925 | 0.4595 | |
|
| No log | 2.8529 | 194 | 0.4305 | 0.6658 | 0.4305 | |
|
| No log | 2.8824 | 196 | 0.3810 | 0.6041 | 0.3810 | |
|
| No log | 2.9118 | 198 | 0.3683 | 0.5923 | 0.3683 | |
|
| No log | 2.9412 | 200 | 0.3942 | 0.6730 | 0.3942 | |
|
| No log | 2.9706 | 202 | 0.5140 | 0.7149 | 0.5140 | |
|
| No log | 3.0 | 204 | 0.5940 | 0.7421 | 0.5940 | |
|
| No log | 3.0294 | 206 | 0.5623 | 0.7362 | 0.5623 | |
|
| No log | 3.0588 | 208 | 0.4522 | 0.7173 | 0.4522 | |
|
| No log | 3.0882 | 210 | 0.4223 | 0.7002 | 0.4223 | |
|
| No log | 3.1176 | 212 | 0.3981 | 0.6730 | 0.3981 | |
|
| No log | 3.1471 | 214 | 0.4195 | 0.6878 | 0.4195 | |
|
| No log | 3.1765 | 216 | 0.4291 | 0.7051 | 0.4291 | |
|
| No log | 3.2059 | 218 | 0.4505 | 0.7132 | 0.4505 | |
|
| No log | 3.2353 | 220 | 0.4684 | 0.7186 | 0.4684 | |
|
| No log | 3.2647 | 222 | 0.4655 | 0.7164 | 0.4655 | |
|
| No log | 3.2941 | 224 | 0.5119 | 0.7264 | 0.5119 | |
|
| No log | 3.3235 | 226 | 0.5486 | 0.7260 | 0.5486 | |
|
| No log | 3.3529 | 228 | 0.4989 | 0.7182 | 0.4989 | |
|
| No log | 3.3824 | 230 | 0.4513 | 0.7010 | 0.4513 | |
|
| No log | 3.4118 | 232 | 0.4255 | 0.6863 | 0.4255 | |
|
| No log | 3.4412 | 234 | 0.4379 | 0.6912 | 0.4379 | |
|
| No log | 3.4706 | 236 | 0.4393 | 0.6995 | 0.4393 | |
|
| No log | 3.5 | 238 | 0.4728 | 0.7068 | 0.4728 | |
|
| No log | 3.5294 | 240 | 0.5134 | 0.7080 | 0.5134 | |
|
| No log | 3.5588 | 242 | 0.4998 | 0.7118 | 0.4998 | |
|
| No log | 3.5882 | 244 | 0.4398 | 0.6887 | 0.4398 | |
|
| No log | 3.6176 | 246 | 0.3836 | 0.6619 | 0.3836 | |
|
| No log | 3.6471 | 248 | 0.3718 | 0.6220 | 0.3718 | |
|
| No log | 3.6765 | 250 | 0.3892 | 0.6566 | 0.3892 | |
|
| No log | 3.7059 | 252 | 0.4497 | 0.6913 | 0.4497 | |
|
| No log | 3.7353 | 254 | 0.5352 | 0.7154 | 0.5352 | |
|
| No log | 3.7647 | 256 | 0.5511 | 0.7103 | 0.5511 | |
|
| No log | 3.7941 | 258 | 0.5689 | 0.7135 | 0.5689 | |
|
| No log | 3.8235 | 260 | 0.5268 | 0.7091 | 0.5268 | |
|
| No log | 3.8529 | 262 | 0.4670 | 0.7000 | 0.4670 | |
|
| No log | 3.8824 | 264 | 0.4545 | 0.7162 | 0.4545 | |
|
| No log | 3.9118 | 266 | 0.4777 | 0.7152 | 0.4777 | |
|
| No log | 3.9412 | 268 | 0.4792 | 0.7175 | 0.4792 | |
|
| No log | 3.9706 | 270 | 0.4656 | 0.7290 | 0.4656 | |
|
| No log | 4.0 | 272 | 0.4576 | 0.7216 | 0.4576 | |
|
| No log | 4.0294 | 274 | 0.4727 | 0.7174 | 0.4727 | |
|
| No log | 4.0588 | 276 | 0.4847 | 0.7224 | 0.4847 | |
|
| No log | 4.0882 | 278 | 0.4756 | 0.7155 | 0.4756 | |
|
| No log | 4.1176 | 280 | 0.5117 | 0.7247 | 0.5117 | |
|
| No log | 4.1471 | 282 | 0.5247 | 0.7208 | 0.5247 | |
|
| No log | 4.1765 | 284 | 0.4861 | 0.7141 | 0.4861 | |
|
| No log | 4.2059 | 286 | 0.4775 | 0.7165 | 0.4775 | |
|
| No log | 4.2353 | 288 | 0.4770 | 0.7156 | 0.4770 | |
|
| No log | 4.2647 | 290 | 0.4946 | 0.7130 | 0.4946 | |
|
| No log | 4.2941 | 292 | 0.5091 | 0.7222 | 0.5091 | |
|
| No log | 4.3235 | 294 | 0.4794 | 0.7122 | 0.4794 | |
|
| No log | 4.3529 | 296 | 0.4423 | 0.7225 | 0.4423 | |
|
| No log | 4.3824 | 298 | 0.4383 | 0.7204 | 0.4383 | |
|
| No log | 4.4118 | 300 | 0.4611 | 0.7092 | 0.4611 | |
|
| No log | 4.4412 | 302 | 0.4751 | 0.7190 | 0.4751 | |
|
| No log | 4.4706 | 304 | 0.4970 | 0.7180 | 0.4970 | |
|
| No log | 4.5 | 306 | 0.4892 | 0.7157 | 0.4892 | |
|
| No log | 4.5294 | 308 | 0.4820 | 0.7191 | 0.4820 | |
|
| No log | 4.5588 | 310 | 0.4822 | 0.7184 | 0.4822 | |
|
| No log | 4.5882 | 312 | 0.4700 | 0.7172 | 0.4700 | |
|
| No log | 4.6176 | 314 | 0.4430 | 0.7173 | 0.4430 | |
|
| No log | 4.6471 | 316 | 0.4170 | 0.7125 | 0.4170 | |
|
| No log | 4.6765 | 318 | 0.4099 | 0.7117 | 0.4099 | |
|
| No log | 4.7059 | 320 | 0.4161 | 0.7093 | 0.4161 | |
|
| No log | 4.7353 | 322 | 0.4317 | 0.7169 | 0.4317 | |
|
| No log | 4.7647 | 324 | 0.4483 | 0.7169 | 0.4483 | |
|
| No log | 4.7941 | 326 | 0.4626 | 0.7199 | 0.4626 | |
|
| No log | 4.8235 | 328 | 0.4702 | 0.7156 | 0.4702 | |
|
| No log | 4.8529 | 330 | 0.4810 | 0.7156 | 0.4810 | |
|
| No log | 4.8824 | 332 | 0.4882 | 0.7155 | 0.4882 | |
|
| No log | 4.9118 | 334 | 0.4916 | 0.7194 | 0.4916 | |
|
| No log | 4.9412 | 336 | 0.4893 | 0.7194 | 0.4893 | |
|
| No log | 4.9706 | 338 | 0.4884 | 0.7157 | 0.4884 | |
|
| No log | 5.0 | 340 | 0.4886 | 0.7157 | 0.4886 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
