O0430HMA5
This model is a fine-tuned version of allenai/OLMo-1B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1441
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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.6508 | 0.09 | 10 | 0.2245 |
0.1822 | 0.18 | 20 | 0.1629 |
0.1562 | 0.27 | 30 | 0.1611 |
0.1546 | 0.36 | 40 | 0.1543 |
0.1503 | 0.45 | 50 | 0.1480 |
0.1521 | 0.54 | 60 | 0.1498 |
0.149 | 0.63 | 70 | 0.1477 |
0.15 | 0.73 | 80 | 0.1572 |
0.1468 | 0.82 | 90 | 0.1505 |
0.15 | 0.91 | 100 | 0.1492 |
0.1513 | 1.0 | 110 | 0.1514 |
0.1459 | 1.09 | 120 | 0.1490 |
0.1466 | 1.18 | 130 | 0.1502 |
0.1471 | 1.27 | 140 | 0.1509 |
0.1485 | 1.36 | 150 | 0.1493 |
0.1456 | 1.45 | 160 | 0.1473 |
0.146 | 1.54 | 170 | 0.1466 |
0.1477 | 1.63 | 180 | 0.1463 |
0.1474 | 1.72 | 190 | 0.1498 |
0.145 | 1.81 | 200 | 0.1504 |
0.1502 | 1.9 | 210 | 0.1490 |
0.1469 | 1.99 | 220 | 0.1485 |
0.1462 | 2.08 | 230 | 0.1464 |
0.1398 | 2.18 | 240 | 0.1457 |
0.1419 | 2.27 | 250 | 0.1467 |
0.1437 | 2.36 | 260 | 0.1483 |
0.1418 | 2.45 | 270 | 0.1457 |
0.1395 | 2.54 | 280 | 0.1456 |
0.1398 | 2.63 | 290 | 0.1459 |
0.1414 | 2.72 | 300 | 0.1439 |
0.1412 | 2.81 | 310 | 0.1439 |
0.1401 | 2.9 | 320 | 0.1440 |
0.1421 | 2.99 | 330 | 0.1441 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
Model tree for Litzy619/O0430HMA5
Base model
allenai/OLMo-1B