<!-- 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. -->
finetuned-baseline-phase-2
This model is a fine-tuned version of ishwarbb23/finetuned-baseline-phase-1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8342
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1408 | 1.36 | 5 | 1.9433 |
| 2.0484 | 2.71 | 10 | 1.9249 |
| 1.934 | 4.07 | 15 | 1.9013 |
| 1.8917 | 5.42 | 20 | 1.8811 |
| 1.9923 | 6.78 | 25 | 1.8662 |
| 1.9 | 8.14 | 30 | 1.8572 |
| 1.8039 | 9.49 | 35 | 1.8497 |
| 1.8909 | 10.85 | 40 | 1.8446 |
| 1.8444 | 12.2 | 45 | 1.8407 |
| 1.7774 | 13.56 | 50 | 1.8370 |
| 1.8487 | 14.92 | 55 | 1.8350 |
| 1.7996 | 16.27 | 60 | 1.8342 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
