| --- |
| library_name: transformers |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: lltransformer-linear-test1 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # lltransformer-linear-test1 |
|
|
| This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 4.3793 |
|
|
| ## Model description |
|
|
| More information needed |
|
|
| ## Intended uses & limitations |
|
|
| More information needed |
|
|
| ## Training and evaluation data |
|
|
| More information needed |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 0.0006 |
| - train_batch_size: 4 |
| - eval_batch_size: 4 |
| - seed: 1234 |
| - gradient_accumulation_steps: 16 |
| - total_train_batch_size: 64 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_ratio: 0.03 |
| - num_epochs: 1 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 6.8532 | 0.0320 | 100 | 6.7483 | |
| | 6.1754 | 0.0640 | 200 | 6.1243 | |
| | 5.8756 | 0.0959 | 300 | 5.7804 | |
| | 5.5348 | 0.1279 | 400 | 5.5261 | |
| | 5.2918 | 0.1599 | 500 | 5.3721 | |
| | 5.329 | 0.1919 | 600 | 5.2467 | |
| | 5.0479 | 0.2239 | 700 | 5.1346 | |
| | 5.0769 | 0.2559 | 800 | 5.0477 | |
| | 4.9082 | 0.2878 | 900 | 4.9726 | |
| | 4.8851 | 0.3198 | 1000 | 4.9025 | |
| | 4.8578 | 0.3518 | 1100 | 4.8424 | |
| | 4.7683 | 0.3838 | 1200 | 4.7891 | |
| | 4.7845 | 0.4158 | 1300 | 4.7421 | |
| | 4.7651 | 0.4477 | 1400 | 4.6986 | |
| | 4.6101 | 0.4797 | 1500 | 4.6589 | |
| | 4.5814 | 0.5117 | 1600 | 4.6180 | |
| | 4.5607 | 0.5437 | 1700 | 4.5858 | |
| | 4.62 | 0.5757 | 1800 | 4.5545 | |
| | 4.4465 | 0.6076 | 1900 | 4.5254 | |
| | 4.5038 | 0.6396 | 2000 | 4.5018 | |
| | 4.4746 | 0.6716 | 2100 | 4.4765 | |
| | 4.4328 | 0.7036 | 2200 | 4.4544 | |
| | 4.4182 | 0.7356 | 2300 | 4.4368 | |
| | 4.4987 | 0.7676 | 2400 | 4.4215 | |
| | 4.4017 | 0.7995 | 2500 | 4.4085 | |
| | 4.4284 | 0.8315 | 2600 | 4.3983 | |
| | 4.3105 | 0.8635 | 2700 | 4.3901 | |
| | 4.2949 | 0.8955 | 2800 | 4.3846 | |
| | 4.3673 | 0.9275 | 2900 | 4.3812 | |
| | 4.3048 | 0.9594 | 3000 | 4.3796 | |
| | 4.4036 | 0.9914 | 3100 | 4.3793 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.51.3 |
| - Pytorch 2.7.0+cu128 |
| - Datasets 3.5.0 |
| - Tokenizers 0.21.1 |
|
|
