jordyvl/test_implementation

1---2license: apache-2.03base_model: bert-base-uncased4tags:5- generated_from_trainer6datasets:7- arxiv_dataset8metrics:9- accuracy10- precision11- recall12- f113model-index:14- name: test_implementation15  results:16  - task:17      name: Text Classification18      type: text-classification19    dataset:20      name: arxiv_dataset21      type: arxiv_dataset22      config: default23      split: train24      args: default25    metrics:26    - name: Accuracy27      type: accuracy28      value: 0.592575914865696829    - name: Precision30      type: precision31      value: 0.0090438387600064832    - name: Recall33      type: recall34      value: 0.3750575241601472635    - name: F136      type: f137      value: 0.01766179504516218438---39 40<!-- This model card has been generated automatically according to the information the Trainer had access to. You41should probably proofread and complete it, then remove this comment. -->42 43# test_implementation44 45This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the arxiv_dataset dataset.46It achieves the following results on the evaluation set:47- Loss: 0.673648- Accuracy: 0.592649- Precision: 0.009050- Recall: 0.375151- F1: 0.017752- Hamming: 0.407453 54## Model description55 56More information needed57 58## Intended uses & limitations59 60More information needed61 62## Training and evaluation data63 64More information needed65 66## Training procedure67 68### Training hyperparameters69 70The following hyperparameters were used during training:71- learning_rate: 2e-0572- train_batch_size: 873- eval_batch_size: 874- seed: 4275- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0876- lr_scheduler_type: linear77- lr_scheduler_warmup_ratio: 0.178- training_steps: 1079 80### Training results81 82| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Hamming |83|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|84| 0.7077        | 0.0   | 5    | 0.6857          | 0.5529   | 0.0089    | 0.4040 | 0.0173 | 0.4471  |85| 0.6801        | 0.0   | 10   | 0.6736          | 0.5926   | 0.0090    | 0.3751 | 0.0177 | 0.4074  |86 87 88### Framework versions89 90- Transformers 4.37.291- Pytorch 1.12.1+cu11392- Datasets 2.16.193- Tokenizers 0.15.194