| | --- |
| | license: apache-2.0 |
| | base_model: allenai/OLMo-1B |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: O0513MA |
| | results: [] |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # O0513MA |
| |
|
| | This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.1456 |
| |
|
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 3.2491 | 0.09 | 10 | 1.4949 | |
| | | 0.7419 | 0.18 | 20 | 0.2008 | |
| | | 0.1742 | 0.27 | 30 | 0.1637 | |
| | | 0.1554 | 0.36 | 40 | 0.1571 | |
| | | 0.1519 | 0.45 | 50 | 0.1515 | |
| | | 0.1531 | 0.54 | 60 | 0.1494 | |
| | | 0.1497 | 0.63 | 70 | 0.1489 | |
| | | 0.1488 | 0.73 | 80 | 0.1584 | |
| | | 0.148 | 0.82 | 90 | 0.1510 | |
| | | 0.1476 | 0.91 | 100 | 0.1509 | |
| | | 0.1499 | 1.0 | 110 | 0.1486 | |
| | | 0.1456 | 1.09 | 120 | 0.1507 | |
| | | 0.1447 | 1.18 | 130 | 0.1518 | |
| | | 0.1472 | 1.27 | 140 | 0.1486 | |
| | | 0.148 | 1.36 | 150 | 0.1490 | |
| | | 0.1455 | 1.45 | 160 | 0.1487 | |
| | | 0.1463 | 1.54 | 170 | 0.1473 | |
| | | 0.1475 | 1.63 | 180 | 0.1475 | |
| | | 0.1479 | 1.72 | 190 | 0.1505 | |
| | | 0.1454 | 1.81 | 200 | 0.1487 | |
| | | 0.1499 | 1.9 | 210 | 0.1480 | |
| | | 0.1474 | 1.99 | 220 | 0.1498 | |
| | | 0.1464 | 2.08 | 230 | 0.1472 | |
| | | 0.1401 | 2.18 | 240 | 0.1462 | |
| | | 0.1419 | 2.27 | 250 | 0.1483 | |
| | | 0.1426 | 2.36 | 260 | 0.1477 | |
| | | 0.141 | 2.45 | 270 | 0.1461 | |
| | | 0.1402 | 2.54 | 280 | 0.1468 | |
| | | 0.1393 | 2.63 | 290 | 0.1469 | |
| | | 0.1426 | 2.72 | 300 | 0.1455 | |
| | | 0.1417 | 2.81 | 310 | 0.1454 | |
| | | 0.1408 | 2.9 | 320 | 0.1456 | |
| | | 0.1424 | 2.99 | 330 | 0.1456 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.36.0.dev0 |
| | - Pytorch 2.1.2+cu121 |
| | - Datasets 2.14.6 |
| | - Tokenizers 0.14.0 |
| |
|
