| ======================================= |
| Model Training Summary |
| ======================================= |
| Model: prajjwal1/bert-mini |
| Task: wnli |
| Training Date: Sat Sep 6 02:39:34 PM JST 2025 |
|
|
| Hyperparameters: |
| - Epochs: 5 |
| - Batch Size: 32 |
| - Learning Rate: 2e-5 |
| - Warmup Steps: 200 |
| - Weight Decay: 0.01 |
| - Max Sequence Length: 128 |
|
|
| Training Status: SUCCESS |
| Job: 12/15 |
|
|
| Model Directory: /home/ubuntu/master-research/not-trust-quivalent/models/wnli/prajjwal1-bert-mini |
| Script Path: /home/ubuntu/master-research/not-trust-quivalent/src/finetune/train.py |
| Output Directory: /home/ubuntu/master-research/not-trust-quivalent/models |
|
|
| ======================================= |
|
|
