genaibook/classifier-chapter4

1---2license: apache-2.03base_model: distilbert-base-uncased4tags:5- generated_from_trainer6datasets:7- ag_news8metrics:9- accuracy10- f111model-index:12- name: trainer-chapter413  results:14  - task:15      name: Text Classification16      type: text-classification17    dataset:18      name: ag_news19      type: ag_news20      config: default21      split: test22      args: default23    metrics:24    - name: Accuracy25      type: accuracy26      value: 0.913026315789473727    - name: F128      type: f129      value: 0.91303018904139830---31 32<!-- This model card has been generated automatically according to the information the Trainer had access to. You33should probably proofread and complete it, then remove this comment. -->34 35# trainer-chapter436 37This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ag_news dataset.38It achieves the following results on the evaluation set:39- Loss: 0.271340- Accuracy: 0.913041- F1: 0.913042 43## Model description44 45More information needed46 47## Intended uses & limitations48 49More information needed50 51## Training and evaluation data52 53More information needed54 55## Training procedure56 57### Training hyperparameters58 59The following hyperparameters were used during training:60- learning_rate: 5e-0561- train_batch_size: 3262- eval_batch_size: 3263- seed: 4264- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0865- lr_scheduler_type: linear66- num_epochs: 267 68### Training results69 70| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |71|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|72| No log        | 1.0   | 313  | 0.2816          | 0.9046   | 0.9042 |73| 0.2967        | 2.0   | 626  | 0.2713          | 0.9130   | 0.9130 |74 75 76### Framework versions77 78- Transformers 4.34.179- Pytorch 2.0.1+cu11880- Datasets 2.14.481- Tokenizers 0.14.082