| | --- |
| | library_name: transformers |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: checkpoints |
| | 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. --> |
| |
|
| | # checkpoints |
| |
|
| | 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: 4.2456 |
| |
|
| | ## 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: 0.0003 |
| | - train_batch_size: 48 |
| | - eval_batch_size: 48 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 2 |
| | - total_train_batch_size: 96 |
| | - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| | - lr_scheduler_type: cosine |
| | - lr_scheduler_warmup_steps: 2000 |
| | - num_epochs: 2 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:------:|:-----:|:---------------:| |
| | | 7.4032 | 0.0845 | 500 | 7.3898 | |
| | | 6.6372 | 0.1689 | 1000 | 6.6140 | |
| | | 6.0337 | 0.2534 | 1500 | 6.0218 | |
| | | 5.4855 | 0.3379 | 2000 | 5.4488 | |
| | | 5.1721 | 0.4224 | 2500 | 5.1130 | |
| | | 4.9505 | 0.5068 | 3000 | 4.9257 | |
| | | 4.8270 | 0.5913 | 3500 | 4.7984 | |
| | | 4.7426 | 0.6758 | 4000 | 4.7051 | |
| | | 4.6787 | 0.7603 | 4500 | 4.6291 | |
| | | 4.6144 | 0.8447 | 5000 | 4.5660 | |
| | | 4.5467 | 0.9292 | 5500 | 4.5108 | |
| | | 4.4913 | 1.0137 | 6000 | 4.4702 | |
| | | 4.4524 | 1.0982 | 6500 | 4.4297 | |
| | | 4.3943 | 1.1826 | 7000 | 4.3960 | |
| | | 4.4030 | 1.2671 | 7500 | 4.3625 | |
| | | 4.4039 | 1.3516 | 8000 | 4.3367 | |
| | | 4.3564 | 1.4361 | 8500 | 4.3136 | |
| | | 4.3499 | 1.5205 | 9000 | 4.2927 | |
| | | 4.3203 | 1.6050 | 9500 | 4.2759 | |
| | | 4.3136 | 1.6895 | 10000 | 4.2620 | |
| | | 4.3009 | 1.7739 | 10500 | 4.2538 | |
| | | 4.2919 | 1.8584 | 11000 | 4.2478 | |
| | | 4.2787 | 1.9429 | 11500 | 4.2456 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 5.0.0 |
| | - Pytorch 2.8.0+cu128 |
| | - Datasets 4.5.0 |
| | - Tokenizers 0.22.2 |
| |
|
