V0422MADP8B
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: 0.1474
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 |
---|---|---|---|
5.8428 | 0.09 | 10 | 2.3011 |
3.8019 | 0.18 | 20 | 1.5011 |
1.0644 | 0.27 | 30 | 0.5040 |
0.2886 | 0.36 | 40 | 0.2186 |
0.1731 | 0.45 | 50 | 0.1452 |
0.1635 | 0.54 | 60 | 0.1457 |
0.1574 | 0.63 | 70 | 0.1521 |
0.1584 | 0.73 | 80 | 0.1515 |
0.18 | 0.82 | 90 | 0.1887 |
0.167 | 0.91 | 100 | 0.1656 |
0.1696 | 1.0 | 110 | 0.1662 |
0.1667 | 1.09 | 120 | 0.1703 |
0.1858 | 1.18 | 130 | 0.1742 |
0.1668 | 1.27 | 140 | 0.1581 |
0.1743 | 1.36 | 150 | 0.1651 |
0.1582 | 1.45 | 160 | 0.1499 |
0.1559 | 1.54 | 170 | 0.1592 |
0.1592 | 1.63 | 180 | 0.1520 |
0.1574 | 1.72 | 190 | 0.1545 |
0.1583 | 1.81 | 200 | 0.1523 |
0.1661 | 1.9 | 210 | 0.1628 |
0.159 | 1.99 | 220 | 0.1527 |
0.1561 | 2.08 | 230 | 0.1493 |
0.1479 | 2.18 | 240 | 0.1483 |
0.1494 | 2.27 | 250 | 0.1485 |
0.1506 | 2.36 | 260 | 0.1482 |
0.1486 | 2.45 | 270 | 0.1487 |
0.1471 | 2.54 | 280 | 0.1486 |
0.148 | 2.63 | 290 | 0.1473 |
0.1467 | 2.72 | 300 | 0.1474 |
0.1487 | 2.81 | 310 | 0.1474 |
0.1501 | 2.9 | 320 | 0.1473 |
0.1508 | 2.99 | 330 | 0.1474 |
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/V0422MADP8B
Base model
microsoft/phi-2