| | --- |
| | license: apache-2.0 |
| | base_model: allenai/OLMo-1B |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: O0430HMA2 |
| | 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. --> |
| |
|
| | # O0430HMA2 |
| |
|
| | 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: 0.0294 |
| |
|
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 2.7246 | 0.09 | 10 | 0.1959 | |
| | | 0.1775 | 0.18 | 20 | 0.1537 | |
| | | 0.1537 | 0.27 | 30 | 0.1589 | |
| | | 0.1516 | 0.36 | 40 | 0.1523 | |
| | | 0.1518 | 0.45 | 50 | 0.1481 | |
| | | 0.1508 | 0.54 | 60 | 0.1490 | |
| | | 0.1514 | 0.63 | 70 | 0.1474 | |
| | | 0.1499 | 0.73 | 80 | 0.1540 | |
| | | 0.1476 | 0.82 | 90 | 0.1486 | |
| | | 0.1447 | 0.91 | 100 | 0.1347 | |
| | | 0.1356 | 1.0 | 110 | 0.0905 | |
| | | 0.0979 | 1.09 | 120 | 0.0900 | |
| | | 0.3159 | 1.18 | 130 | 0.0714 | |
| | | 0.3542 | 1.27 | 140 | 0.0738 | |
| | | 0.085 | 1.36 | 150 | 0.0609 | |
| | | 0.0639 | 1.45 | 160 | 0.0610 | |
| | | 0.0555 | 1.54 | 170 | 0.0549 | |
| | | 0.067 | 1.63 | 180 | 0.0581 | |
| | | 0.1336 | 1.72 | 190 | 0.0647 | |
| | | 0.0592 | 1.81 | 200 | 0.0594 | |
| | | 0.059 | 1.9 | 210 | 0.0561 | |
| | | 0.0585 | 1.99 | 220 | 0.0543 | |
| | | 0.0577 | 2.08 | 230 | 0.0547 | |
| | | 0.0528 | 2.18 | 240 | 0.0567 | |
| | | 0.0516 | 2.27 | 250 | 0.0511 | |
| | | 0.0533 | 2.36 | 260 | 0.0455 | |
| | | 0.0428 | 2.45 | 270 | 0.0457 | |
| | | 0.0386 | 2.54 | 280 | 0.0384 | |
| | | 0.0386 | 2.63 | 290 | 0.0344 | |
| | | 0.0343 | 2.72 | 300 | 0.0324 | |
| | | 0.0311 | 2.81 | 310 | 0.0303 | |
| | | 0.0337 | 2.9 | 320 | 0.0296 | |
| | | 0.0334 | 2.99 | 330 | 0.0294 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.36.0.dev0 |
| | - Pytorch 2.1.2+cu121 |
| | - Datasets 2.14.6 |
| | - Tokenizers 0.14.1 |
| |
|
