finale-mlp-linear-9L
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1081
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: 0.0005
- train_batch_size: 80
- eval_batch_size: 80
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 1280
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- training_steps: 750
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 102.0503 | 0.0674 | 50 | 5.6659 |
| 77.5119 | 0.1348 | 100 | 4.6899 |
| 70.3764 | 0.2022 | 150 | 4.2638 |
| 63.8118 | 0.2696 | 200 | 3.9344 |
| 61.1106 | 0.3370 | 250 | 3.7483 |
| 58.3348 | 0.4044 | 300 | 3.6138 |
| 56.6996 | 0.4719 | 350 | 3.4927 |
| 54.9361 | 0.5393 | 400 | 3.4158 |
| 53.8945 | 0.6067 | 450 | 3.3447 |
| 52.8687 | 0.6741 | 500 | 3.2968 |
| 52.3214 | 0.7415 | 550 | 3.2509 |
| 51.4070 | 0.8089 | 600 | 3.2120 |
| 50.8616 | 0.8763 | 650 | 3.1778 |
| 50.1968 | 0.9437 | 700 | 3.1350 |
| 49.7485 | 1.0108 | 750 | 3.1081 |
Framework versions
- Transformers 5.15.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 5.0.1
- Tokenizers 0.22.2
- Downloads last month
- -