|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: finetuned-bert-categories-estimation |
|
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. --> |
|
|
|
# finetuned-bert-categories-estimation |
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4354 |
|
- F1: 0.9168 |
|
- Accuracy: 0.9383 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| 0.1375 | 0.15 | 100 | 0.4396 | 0.8593 | 0.9085 | |
|
| 0.1136 | 0.29 | 200 | 0.4757 | 0.8533 | 0.8988 | |
|
| 0.1273 | 0.44 | 300 | 0.4634 | 0.8637 | 0.9054 | |
|
| 0.1202 | 0.59 | 400 | 0.4444 | 0.8638 | 0.9091 | |
|
| 0.1372 | 0.73 | 500 | 0.4322 | 0.8708 | 0.9106 | |
|
| 0.1598 | 0.88 | 600 | 0.4442 | 0.8734 | 0.9115 | |
|
| 0.1918 | 1.03 | 700 | 0.4158 | 0.8715 | 0.9107 | |
|
| 0.1404 | 1.17 | 800 | 0.4295 | 0.8772 | 0.9115 | |
|
| 0.1479 | 1.32 | 900 | 0.4024 | 0.8849 | 0.9190 | |
|
| 0.1374 | 1.47 | 1000 | 0.4125 | 0.8798 | 0.9170 | |
|
| 0.1504 | 1.62 | 1100 | 0.3967 | 0.8857 | 0.9201 | |
|
| 0.1204 | 1.76 | 1200 | 0.3960 | 0.8860 | 0.9201 | |
|
| 0.1449 | 1.91 | 1300 | 0.4093 | 0.8890 | 0.9177 | |
|
| 0.1208 | 2.06 | 1400 | 0.4064 | 0.8841 | 0.9203 | |
|
| 0.0884 | 2.2 | 1500 | 0.4128 | 0.8881 | 0.9203 | |
|
| 0.1073 | 2.35 | 1600 | 0.3934 | 0.8940 | 0.9243 | |
|
| 0.0937 | 2.5 | 1700 | 0.4158 | 0.8888 | 0.9196 | |
|
| 0.0931 | 2.64 | 1800 | 0.4028 | 0.8903 | 0.9230 | |
|
| 0.0967 | 2.79 | 1900 | 0.4015 | 0.9001 | 0.9269 | |
|
| 0.094 | 2.94 | 2000 | 0.4116 | 0.8970 | 0.9258 | |
|
| 0.074 | 3.08 | 2100 | 0.4183 | 0.8978 | 0.9251 | |
|
| 0.0593 | 3.23 | 2200 | 0.4177 | 0.8971 | 0.9262 | |
|
| 0.085 | 3.38 | 2300 | 0.3933 | 0.9092 | 0.9306 | |
|
| 0.0764 | 3.52 | 2400 | 0.4245 | 0.9008 | 0.9276 | |
|
| 0.0849 | 3.67 | 2500 | 0.4044 | 0.8983 | 0.9273 | |
|
| 0.0833 | 3.82 | 2600 | 0.4089 | 0.9021 | 0.9286 | |
|
| 0.1134 | 3.96 | 2700 | 0.4212 | 0.8989 | 0.9251 | |
|
| 0.0572 | 4.11 | 2800 | 0.4295 | 0.9056 | 0.9275 | |
|
| 0.0651 | 4.26 | 2900 | 0.4111 | 0.9010 | 0.9267 | |
|
| 0.0524 | 4.41 | 3000 | 0.3951 | 0.9064 | 0.9309 | |
|
| 0.0572 | 4.55 | 3100 | 0.4091 | 0.9030 | 0.9282 | |
|
| 0.0585 | 4.7 | 3200 | 0.4222 | 0.9003 | 0.9275 | |
|
| 0.0615 | 4.85 | 3300 | 0.4134 | 0.9056 | 0.9311 | |
|
| 0.0663 | 4.99 | 3400 | 0.4200 | 0.9046 | 0.9293 | |
|
| 0.028 | 5.14 | 3500 | 0.4131 | 0.9057 | 0.9331 | |
|
| 0.0196 | 5.29 | 3600 | 0.4436 | 0.9017 | 0.9293 | |
|
| 0.0237 | 5.43 | 3700 | 0.4316 | 0.9054 | 0.9309 | |
|
| 0.0278 | 5.58 | 3800 | 0.4364 | 0.9017 | 0.9280 | |
|
| 0.0352 | 5.73 | 3900 | 0.4294 | 0.9021 | 0.9284 | |
|
| 0.0547 | 5.87 | 4000 | 0.4202 | 0.9098 | 0.9320 | |
|
| 0.0512 | 6.02 | 4100 | 0.4280 | 0.9083 | 0.9311 | |
|
| 0.0201 | 6.17 | 4200 | 0.4336 | 0.9099 | 0.9311 | |
|
| 0.0192 | 6.31 | 4300 | 0.4329 | 0.9078 | 0.9330 | |
|
| 0.0167 | 6.46 | 4400 | 0.4318 | 0.9091 | 0.9331 | |
|
| 0.0305 | 6.61 | 4500 | 0.4288 | 0.9085 | 0.9333 | |
|
| 0.0178 | 6.75 | 4600 | 0.4269 | 0.9111 | 0.9337 | |
|
| 0.0268 | 6.9 | 4700 | 0.4267 | 0.9114 | 0.9337 | |
|
| 0.0207 | 7.05 | 4800 | 0.4281 | 0.9115 | 0.9344 | |
|
| 0.0116 | 7.2 | 4900 | 0.4329 | 0.9111 | 0.9348 | |
|
| 0.0104 | 7.34 | 5000 | 0.4445 | 0.9089 | 0.9335 | |
|
| 0.0149 | 7.49 | 5100 | 0.4394 | 0.9114 | 0.9343 | |
|
| 0.0084 | 7.64 | 5200 | 0.4367 | 0.9145 | 0.9350 | |
|
| 0.0151 | 7.78 | 5300 | 0.4460 | 0.9087 | 0.9319 | |
|
| 0.012 | 7.93 | 5400 | 0.4368 | 0.9130 | 0.9354 | |
|
| 0.0083 | 8.08 | 5500 | 0.4354 | 0.9122 | 0.9350 | |
|
| 0.0089 | 8.22 | 5600 | 0.4319 | 0.9120 | 0.9344 | |
|
| 0.0063 | 8.37 | 5700 | 0.4304 | 0.9139 | 0.9359 | |
|
| 0.0089 | 8.52 | 5800 | 0.4297 | 0.9136 | 0.9352 | |
|
| 0.0081 | 8.66 | 5900 | 0.4348 | 0.9128 | 0.9348 | |
|
| 0.0084 | 8.81 | 6000 | 0.4361 | 0.9126 | 0.9354 | |
|
| 0.0051 | 8.96 | 6100 | 0.4373 | 0.9140 | 0.9366 | |
|
| 0.0049 | 9.1 | 6200 | 0.4374 | 0.9167 | 0.9376 | |
|
| 0.0049 | 9.25 | 6300 | 0.4349 | 0.9170 | 0.9377 | |
|
| 0.004 | 9.4 | 6400 | 0.4358 | 0.9174 | 0.9385 | |
|
| 0.0046 | 9.54 | 6500 | 0.4352 | 0.9175 | 0.9385 | |
|
| 0.0108 | 9.69 | 6600 | 0.4355 | 0.9171 | 0.9381 | |
|
| 0.0039 | 9.84 | 6700 | 0.4357 | 0.9168 | 0.9383 | |
|
| 0.0053 | 9.99 | 6800 | 0.4354 | 0.9168 | 0.9383 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
