CodeIsAbstract/HybridModelScratch

1---2library_name: transformers3tags:4- generated_from_trainer5metrics:6- accuracy7model-index:8- name: HybridModelScratch9  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# HybridModelScratch16 17This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.18It achieves the following results on the evaluation set:19- Loss: 6.019120- Accuracy: 0.152821 22## Model description23 24More information needed25 26## Intended uses & limitations27 28More information needed29 30## Training and evaluation data31 32More information needed33 34## Training procedure35 36### Training hyperparameters37 38The following hyperparameters were used during training:39- learning_rate: 0.000140- train_batch_size: 6441- eval_batch_size: 1642- seed: 4243- distributed_type: multi-GPU44- num_devices: 245- gradient_accumulation_steps: 846- total_train_batch_size: 102447- total_eval_batch_size: 3248- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments49- lr_scheduler_type: cosine50- lr_scheduler_warmup_steps: 15051- training_steps: 200052 53### Training results54 55| Training Loss | Epoch | Step | Validation Loss | Accuracy |56|:-------------:|:-----:|:----:|:---------------:|:--------:|57| 133.1257      | 0.05  | 100  | 7.7065          | 0.0876   |58| 107.0186      | 0.1   | 200  | 6.6099          | 0.1364   |59| 102.3462      | 0.15  | 300  | 6.3677          | 0.1448   |60| 99.0524       | 0.2   | 400  | 6.2145          | 0.1531   |61| 96.6031       | 0.25  | 500  | 6.1010          | 0.1584   |62| 95.9314       | 0.3   | 600  | 5.9869          | 0.1640   |63| 95.0101       | 0.35  | 700  | 5.8890          | 0.1683   |64| 94.2643       | 0.4   | 800  | 5.8284          | 0.1715   |65| 93.2266       | 0.45  | 900  | 5.7744          | 0.1746   |66| 92.0125       | 0.5   | 1000 | 5.7337          | 0.1763   |67| 95.8613       | 0.55  | 1100 | 6.0068          | 0.1554   |68| 98.1012       | 0.6   | 1200 | 6.1055          | 0.1491   |69| 97.152        | 0.65  | 1300 | 6.0546          | 0.1512   |70| 97.8734       | 0.7   | 1400 | 6.0947          | 0.1474   |71| 97.4964       | 0.75  | 1500 | 6.0419          | 0.1510   |72| 97.562        | 0.8   | 1600 | 6.0272          | 0.1518   |73| 97.3206       | 0.85  | 1700 | 6.0171          | 0.1529   |74| 96.8684       | 0.9   | 1800 | 6.0163          | 0.1532   |75| 96.472        | 0.95  | 1900 | 6.0193          | 0.1528   |76| 96.5051       | 1.0   | 2000 | 6.0191          | 0.1528   |77 78 79### Framework versions80 81- Transformers 4.56.082- Pytorch 2.8.0+cu12983- Datasets 5.0.084- Tokenizers 0.22.085