V0424MADP1
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: 0.1465
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 |
---|---|---|---|
8.4007 | 0.09 | 10 | 2.9550 |
4.3018 | 0.18 | 20 | 1.6770 |
0.9639 | 0.27 | 30 | 0.4753 |
0.228 | 0.36 | 40 | 0.2016 |
0.1702 | 0.45 | 50 | 0.1662 |
0.1615 | 0.54 | 60 | 0.1537 |
0.1573 | 0.63 | 70 | 0.1545 |
0.1578 | 0.73 | 80 | 0.1467 |
0.1516 | 0.82 | 90 | 0.1460 |
0.1521 | 0.91 | 100 | 0.1453 |
0.154 | 1.0 | 110 | 0.1498 |
0.1499 | 1.09 | 120 | 0.1479 |
0.1523 | 1.18 | 130 | 0.1521 |
0.1526 | 1.27 | 140 | 0.1509 |
0.1563 | 1.36 | 150 | 0.1486 |
0.1535 | 1.45 | 160 | 0.1476 |
0.1535 | 1.54 | 170 | 0.1492 |
0.1536 | 1.63 | 180 | 0.1486 |
0.1527 | 1.72 | 190 | 0.1565 |
0.1518 | 1.81 | 200 | 0.1546 |
0.1592 | 1.9 | 210 | 0.1557 |
0.1535 | 1.99 | 220 | 0.1553 |
0.1549 | 2.08 | 230 | 0.1544 |
0.1466 | 2.18 | 240 | 0.1500 |
0.1465 | 2.27 | 250 | 0.1485 |
0.1488 | 2.36 | 260 | 0.1479 |
0.1473 | 2.45 | 270 | 0.1467 |
0.1471 | 2.54 | 280 | 0.1472 |
0.1454 | 2.63 | 290 | 0.1471 |
0.1465 | 2.72 | 300 | 0.1465 |
0.1468 | 2.81 | 310 | 0.1465 |
0.1485 | 2.9 | 320 | 0.1465 |
0.149 | 2.99 | 330 | 0.1465 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for Litzy619/V0424MADP1
Base model
microsoft/phi-2