--- license: gpl-3.0 base_model: ckiplab/bert-base-chinese tags: - generated_from_trainer model-index: - name: bert_model-1 results: [] --- # bert_model-1 This model is a fine-tuned version of [ckiplab/bert-base-chinese](https://huggingface.co/ckiplab/bert-base-chinese) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4135 ## 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: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.3994 | 0.01 | 100 | 1.6845 | | 1.8101 | 0.03 | 200 | 1.6963 | | 1.7742 | 0.04 | 300 | 1.6679 | | 1.8425 | 0.05 | 400 | 1.6657 | | 1.8452 | 0.06 | 500 | 1.6369 | | 1.8109 | 0.08 | 600 | 1.6471 | | 1.8469 | 0.09 | 700 | 1.6350 | | 1.7709 | 0.1 | 800 | 1.6302 | | 1.7848 | 0.12 | 900 | 1.6346 | | 1.7955 | 0.13 | 1000 | 1.6345 | | 1.79 | 0.14 | 1100 | 1.6356 | | 1.7655 | 0.16 | 1200 | 1.6116 | | 1.7826 | 0.17 | 1300 | 1.6248 | | 1.7651 | 0.18 | 1400 | 1.6262 | | 1.7639 | 0.19 | 1500 | 1.6078 | | 1.7743 | 0.21 | 1600 | 1.6105 | | 1.7672 | 0.22 | 1700 | 1.5910 | | 1.7054 | 0.23 | 1800 | 1.6060 | | 1.6777 | 0.25 | 1900 | 1.6253 | | 1.748 | 0.26 | 2000 | 1.5970 | | 1.7503 | 0.27 | 2100 | 1.5893 | | 1.7329 | 0.29 | 2200 | 1.5883 | | 1.6826 | 0.3 | 2300 | 1.5781 | | 1.7237 | 0.31 | 2400 | 1.5716 | | 1.7358 | 0.32 | 2500 | 1.5671 | | 1.7093 | 0.34 | 2600 | 1.5689 | | 1.6771 | 0.35 | 2700 | 1.5654 | | 1.6924 | 0.36 | 2800 | 1.5729 | | 1.6768 | 0.38 | 2900 | 1.5545 | | 1.7158 | 0.39 | 3000 | 1.5471 | | 1.6808 | 0.4 | 3100 | 1.5415 | | 1.6547 | 0.42 | 3200 | 1.5444 | | 1.6557 | 0.43 | 3300 | 1.5400 | | 1.6491 | 0.44 | 3400 | 1.5358 | | 1.6757 | 0.45 | 3500 | 1.5244 | | 1.6473 | 0.47 | 3600 | 1.5268 | | 1.5987 | 0.48 | 3700 | 1.5201 | | 1.6386 | 0.49 | 3800 | 1.5121 | | 1.6568 | 0.51 | 3900 | 1.5004 | | 1.6454 | 0.52 | 4000 | 1.4895 | | 1.6175 | 0.53 | 4100 | 1.4974 | | 1.6036 | 0.55 | 4200 | 1.4964 | | 1.5785 | 0.56 | 4300 | 1.4882 | | 1.6009 | 0.57 | 4400 | 1.4858 | | 1.5723 | 0.58 | 4500 | 1.4755 | | 1.6133 | 0.6 | 4600 | 1.4751 | | 1.5683 | 0.61 | 4700 | 1.4692 | | 1.5773 | 0.62 | 4800 | 1.4677 | | 1.6005 | 0.64 | 4900 | 1.4645 | | 1.5812 | 0.65 | 5000 | 1.4596 | | 1.577 | 0.66 | 5100 | 1.4506 | | 1.591 | 0.68 | 5200 | 1.4507 | | 1.5609 | 0.69 | 5300 | 1.4474 | | 1.5437 | 0.7 | 5400 | 1.4441 | | 1.5535 | 0.71 | 5500 | 1.4430 | | 1.5882 | 0.73 | 5600 | 1.4398 | | 1.5731 | 0.74 | 5700 | 1.4328 | | 1.5511 | 0.75 | 5800 | 1.4280 | | 1.5455 | 0.77 | 5900 | 1.4358 | | 1.5194 | 0.78 | 6000 | 1.4321 | | 1.5524 | 0.79 | 6100 | 1.4207 | | 1.5406 | 0.81 | 6200 | 1.4215 | | 1.4811 | 0.82 | 6300 | 1.4293 | | 1.5117 | 0.83 | 6400 | 1.4282 | | 1.5197 | 0.84 | 6500 | 1.4109 | | 1.558 | 0.86 | 6600 | 1.4241 | | 1.5277 | 0.87 | 6700 | 1.4116 | | 1.5346 | 0.88 | 6800 | 1.4190 | | 1.4974 | 0.9 | 6900 | 1.4105 | | 1.5345 | 0.91 | 7000 | 1.4163 | | 1.5578 | 0.92 | 7100 | 1.4099 | | 1.496 | 0.94 | 7200 | 1.4120 | | 1.5192 | 0.95 | 7300 | 1.4073 | | 1.456 | 0.96 | 7400 | 1.4105 | | 1.4821 | 0.97 | 7500 | 1.4175 | | 1.5331 | 0.99 | 7600 | 1.4135 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.1.0 - Datasets 2.12.0 - Tokenizers 0.13.3