| --- |
| license: apache-2.0 |
| base_model: allenai/OLMo-1B |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: AOLM2 |
| 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. --> |
|
|
| # AOLM2 |
|
|
| 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: 0.1428 |
|
|
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 2.9303 | 0.09 | 10 | 0.9652 | |
| | 0.3692 | 0.18 | 20 | 0.1604 | |
| | 0.1539 | 0.27 | 30 | 0.1626 | |
| | 0.1561 | 0.36 | 40 | 0.1535 | |
| | 0.1518 | 0.45 | 50 | 0.1511 | |
| | 0.1518 | 0.54 | 60 | 0.1483 | |
| | 0.1488 | 0.63 | 70 | 0.1485 | |
| | 0.1486 | 0.73 | 80 | 0.1528 | |
| | 0.1467 | 0.82 | 90 | 0.1504 | |
| | 0.1476 | 0.91 | 100 | 0.1485 | |
| | 0.149 | 1.0 | 110 | 0.1477 | |
| | 0.1456 | 1.09 | 120 | 0.1490 | |
| | 0.1442 | 1.18 | 130 | 0.1499 | |
| | 0.1474 | 1.27 | 140 | 0.1479 | |
| | 0.1482 | 1.36 | 150 | 0.1486 | |
| | 0.1455 | 1.45 | 160 | 0.1483 | |
| | 0.1455 | 1.54 | 170 | 0.1467 | |
| | 0.1467 | 1.63 | 180 | 0.1455 | |
| | 0.1464 | 1.72 | 190 | 0.1485 | |
| | 0.145 | 1.81 | 200 | 0.1468 | |
| | 0.1485 | 1.9 | 210 | 0.1458 | |
| | 0.1453 | 1.99 | 220 | 0.1477 | |
| | 0.1432 | 2.08 | 230 | 0.1457 | |
| | 0.1376 | 2.18 | 240 | 0.1447 | |
| | 0.1392 | 2.27 | 250 | 0.1446 | |
| | 0.1385 | 2.36 | 260 | 0.1443 | |
| | 0.137 | 2.45 | 270 | 0.1444 | |
| | 0.1352 | 2.54 | 280 | 0.1436 | |
| | 0.1338 | 2.63 | 290 | 0.1435 | |
| | 0.1352 | 2.72 | 300 | 0.1430 | |
| | 0.1351 | 2.81 | 310 | 0.1428 | |
| | 0.1317 | 2.9 | 320 | 0.1430 | |
| | 0.1361 | 2.99 | 330 | 0.1428 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.36.0.dev0 |
| - Pytorch 2.1.2+cu121 |
| - Datasets 2.14.6 |
| - Tokenizers 0.14.1 |
|
|
