V0422MADP2D
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0594
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 60
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.3918 | 0.09 | 10 | 1.3894 |
0.9074 | 0.18 | 20 | 0.1485 |
0.1475 | 0.27 | 30 | 0.1036 |
0.1121 | 0.36 | 40 | 0.0844 |
0.0886 | 0.45 | 50 | 0.0793 |
0.0955 | 0.54 | 60 | 0.0731 |
0.0803 | 0.63 | 70 | 0.0789 |
0.0891 | 0.73 | 80 | 0.0765 |
0.0816 | 0.82 | 90 | 0.0690 |
0.0786 | 0.91 | 100 | 0.0662 |
0.0804 | 1.0 | 110 | 0.0699 |
0.0632 | 1.09 | 120 | 0.0684 |
0.0684 | 1.18 | 130 | 0.0691 |
0.0705 | 1.27 | 140 | 0.0680 |
0.063 | 1.36 | 150 | 0.0676 |
0.0703 | 1.45 | 160 | 0.0644 |
0.0594 | 1.54 | 170 | 0.0656 |
0.063 | 1.63 | 180 | 0.0632 |
0.0576 | 1.72 | 190 | 0.0635 |
0.0621 | 1.81 | 200 | 0.0628 |
0.0584 | 1.9 | 210 | 0.0605 |
0.0579 | 1.99 | 220 | 0.0601 |
0.0432 | 2.08 | 230 | 0.0589 |
0.0422 | 2.18 | 240 | 0.0600 |
0.0364 | 2.27 | 250 | 0.0640 |
0.0377 | 2.36 | 260 | 0.0634 |
0.0397 | 2.45 | 270 | 0.0617 |
0.0361 | 2.54 | 280 | 0.0610 |
0.0335 | 2.63 | 290 | 0.0611 |
0.0384 | 2.72 | 300 | 0.0599 |
0.0386 | 2.81 | 310 | 0.0594 |
0.0392 | 2.9 | 320 | 0.0594 |
0.0408 | 2.99 | 330 | 0.0594 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for Litzy619/V0422MADP2D
Base model
microsoft/phi-2