Toastmachine/exaone_CSAT_test

1---2library_name: peft3license: other4base_model: LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct5tags:6- generated_from_trainer7metrics:8- accuracy9- f110model-index:11- name: exaone_CSAT_test12  results: []13---14 15<!-- This model card has been generated automatically according to the information the Trainer had access to. You16should probably proofread and complete it, then remove this comment. -->17 18# exaone_CSAT_test19 20This model is a fine-tuned version of [LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct) on the None dataset.21It achieves the following results on the evaluation set:22- Loss: 0.479223- Accuracy: 0.562824- F1: 0.596525 26## Model description27 28More information needed29 30## Intended uses & limitations31 32More information needed33 34## Training and evaluation data35 36More information needed37 38## Training procedure39 40### Training hyperparameters41 42The following hyperparameters were used during training:43- learning_rate: 1e-0544- train_batch_size: 245- eval_batch_size: 246- seed: 4247- gradient_accumulation_steps: 248- total_train_batch_size: 449- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments50- lr_scheduler_type: cosine51- lr_scheduler_warmup_steps: 20052- training_steps: 210053 54### Training results55 56| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |57|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|58| 24.6602       | 0.1121 | 50   | 24.1094         | 0.5477   | 0.5761 |59| 12.8586       | 0.2242 | 100  | 6.5703          | 0.5729   | 0.6062 |60| 0.3657        | 0.3363 | 150  | 0.4956          | 0.5678   | 0.6005 |61| 0.5527        | 0.4484 | 200  | 0.4880          | 0.5678   | 0.6005 |62| 0.9587        | 0.5605 | 250  | 0.5098          | 0.5729   | 0.6054 |63| 0.9119        | 0.6726 | 300  | 0.4468          | 0.5678   | 0.6016 |64| 0.0989        | 0.7848 | 350  | 0.4690          | 0.5729   | 0.6066 |65| 0.6981        | 0.8969 | 400  | 0.4612          | 0.5628   | 0.5965 |66| 0.5197        | 1.0090 | 450  | 0.4792          | 0.5628   | 0.5965 |67 68 69### Framework versions70 71- PEFT 0.13.272- Transformers 4.46.273- Pytorch 2.5.1+cu12174- Datasets 3.1.075- Tokenizers 0.20.3