Sunbird/t5_small_language_Classification

1---2library_name: transformers3license: apache-2.04base_model: yigagilbert/t5_efficient_small_language_ID5tags:6- generated_from_trainer7datasets:8- generator9metrics:10- accuracy11- precision12- recall13- f114model-index:15- name: t5_small_language_Classification16  results:17  - task:18      type: text-classification19      name: Text Classification20    dataset:21      name: generator22      type: generator23      config: default24      split: train25      args: default26    metrics:27    - type: accuracy28      value: 0.65887960538166329      name: Accuracy30    - type: precision31      value: 0.692846941908649732      name: Precision33    - type: recall34      value: 0.65887960538166335      name: Recall36    - type: f137      value: 0.628636910478207638      name: F139---40 41<!-- This model card has been generated automatically according to the information the Trainer had access to. You42should probably proofread and complete it, then remove this comment. -->43 44# t5_small_language_Classification45 46This model is a fine-tuned version of [yigagilbert/t5_efficient_small_language_ID](https://huggingface.co/yigagilbert/t5_efficient_small_language_ID) on the generator dataset.47It achieves the following results on the evaluation set:48- Loss: 1.648249- Accuracy: 0.658950- Precision: 0.692851- Recall: 0.658952- F1: 0.628653 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: 0.000572- train_batch_size: 6473- eval_batch_size: 6474- seed: 4275- gradient_accumulation_steps: 276- total_train_batch_size: 12877- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments78- lr_scheduler_type: cosine_with_restarts79- lr_scheduler_warmup_steps: 100080- training_steps: 6000081 82### Training results83 84| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |85|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|86| 0.6453        | 0.0083 | 500  | 1.7792          | 0.5575   | 0.6272    | 0.5575 | 0.5283 |87| 0.3701        | 0.0167 | 1000 | 2.8566          | 0.4925   | 0.6309    | 0.4925 | 0.4427 |88| 0.3602        | 0.025  | 1500 | 3.4108          | 0.4331   | 0.6188    | 0.4331 | 0.3903 |89| 0.3573        | 0.0333 | 2000 | 1.9821          | 0.5855   | 0.6303    | 0.5855 | 0.5419 |90| 0.4229        | 0.0417 | 2500 | 1.9248          | 0.6071   | 0.6712    | 0.6071 | 0.5731 |91| 0.2156        | 0.05   | 3000 | 2.6673          | 0.5217   | 0.6906    | 0.5217 | 0.4851 |92| 0.3752        | 0.0583 | 3500 | 1.9381          | 0.5984   | 0.6682    | 0.5984 | 0.5619 |93| 0.4996        | 0.0667 | 4000 | 1.5622          | 0.6266   | 0.6757    | 0.6266 | 0.6022 |94| 0.2773        | 0.075  | 4500 | 1.8355          | 0.6299   | 0.6892    | 0.6299 | 0.5872 |95| 0.2815        | 0.0833 | 5000 | 1.7752          | 0.6423   | 0.6905    | 0.6423 | 0.6034 |96| 0.2525        | 0.0917 | 5500 | 1.6552          | 0.6450   | 0.6879    | 0.6450 | 0.6082 |97| 0.2271        | 0.1    | 6000 | 1.6523          | 0.6575   | 0.6916    | 0.6575 | 0.6278 |98| 0.3591        | 0.1083 | 6500 | 1.7169          | 0.6542   | 0.6985    | 0.6542 | 0.6238 |99| 0.2659        | 0.1167 | 7000 | 1.7209          | 0.6439   | 0.7090    | 0.6439 | 0.6180 |100| 0.2337        | 0.125  | 7500 | 1.7631          | 0.6531   | 0.7019    | 0.6531 | 0.6158 |101 102 103### Framework versions104 105- Transformers 4.57.1106- Pytorch 2.9.0+cu128107- Datasets 4.3.0108- Tokenizers 0.22.1109