Realgon/N_bert_imdb_padding0model

1---2license: apache-2.03base_model: bert-base-uncased4tags:5- generated_from_trainer6datasets:7- imdb8metrics:9- accuracy10model-index:11- name: N_bert_imdb_padding0model12  results:13  - task:14      name: Text Classification15      type: text-classification16    dataset:17      name: imdb18      type: imdb19      config: plain_text20      split: test21      args: plain_text22    metrics:23    - name: Accuracy24      type: accuracy25      value: 0.9405226---27 28<!-- This model card has been generated automatically according to the information the Trainer had access to. You29should probably proofread and complete it, then remove this comment. -->30 31# N_bert_imdb_padding0model32 33This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the imdb dataset.34It achieves the following results on the evaluation set:35- Loss: 0.657536- Accuracy: 0.940537 38## Model description39 40More information needed41 42## Intended uses & limitations43 44More information needed45 46## Training and evaluation data47 48More information needed49 50## Training procedure51 52### Training hyperparameters53 54The following hyperparameters were used during training:55- learning_rate: 2e-0556- train_batch_size: 1657- eval_batch_size: 1658- seed: 4259- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0860- lr_scheduler_type: linear61- num_epochs: 2062 63### Training results64 65| Training Loss | Epoch | Step  | Validation Loss | Accuracy |66|:-------------:|:-----:|:-----:|:---------------:|:--------:|67| 0.2204        | 1.0   | 1563  | 0.2086          | 0.9332   |68| 0.1501        | 2.0   | 3126  | 0.2195          | 0.9356   |69| 0.0871        | 3.0   | 4689  | 0.3156          | 0.935    |70| 0.0555        | 4.0   | 6252  | 0.3170          | 0.9314   |71| 0.0362        | 5.0   | 7815  | 0.3568          | 0.9353   |72| 0.0282        | 6.0   | 9378  | 0.4438          | 0.9380   |73| 0.0199        | 7.0   | 10941 | 0.4900          | 0.9357   |74| 0.0219        | 8.0   | 12504 | 0.4963          | 0.9344   |75| 0.0115        | 9.0   | 14067 | 0.5554          | 0.9333   |76| 0.0078        | 10.0  | 15630 | 0.5974          | 0.9340   |77| 0.0087        | 11.0  | 17193 | 0.6081          | 0.9360   |78| 0.0038        | 12.0  | 18756 | 0.5909          | 0.9322   |79| 0.0096        | 13.0  | 20319 | 0.6002          | 0.9381   |80| 0.0061        | 14.0  | 21882 | 0.5645          | 0.9372   |81| 0.0057        | 15.0  | 23445 | 0.6415          | 0.9388   |82| 0.0019        | 16.0  | 25008 | 0.6901          | 0.9388   |83| 0.0005        | 17.0  | 26571 | 0.7099          | 0.9389   |84| 0.0           | 18.0  | 28134 | 0.7022          | 0.9392   |85| 0.0008        | 19.0  | 29697 | 0.6640          | 0.9398   |86| 0.0           | 20.0  | 31260 | 0.6575          | 0.9405   |87 88 89### Framework versions90 91- Transformers 4.33.292- Pytorch 2.0.1+cu11793- Datasets 2.14.594- Tokenizers 0.13.395