--- license: apache-2.0 base_model: allenai/OLMo-1B tags: - generated_from_trainer model-index: - name: O0430HMA9 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. --> # O0430HMA9 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: 0.0218 ## 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: 100 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.681 | 0.09 | 10 | 0.1921 | | 0.1704 | 0.18 | 20 | 0.1533 | | 0.1507 | 0.27 | 30 | 0.1619 | | 0.1544 | 0.36 | 40 | 0.1492 | | 0.1502 | 0.45 | 50 | 0.1504 | | 0.1515 | 0.54 | 60 | 0.1479 | | 0.1509 | 0.63 | 70 | 0.1470 | | 0.1492 | 0.73 | 80 | 0.1537 | | 0.1475 | 0.82 | 90 | 0.1494 | | 0.1482 | 0.91 | 100 | 0.1473 | | 0.1615 | 1.0 | 110 | 0.1788 | | 0.316 | 1.09 | 120 | 0.3899 | | 0.1295 | 1.18 | 130 | 0.0776 | | 0.0766 | 1.27 | 140 | 0.0779 | | 0.0675 | 1.36 | 150 | 0.0348 | | 0.1236 | 1.45 | 160 | 0.0590 | | 0.1126 | 1.54 | 170 | 0.0556 | | 0.0687 | 1.63 | 180 | 0.0329 | | 0.142 | 1.72 | 190 | 0.8702 | | 0.1355 | 1.81 | 200 | 0.1972 | | 0.0663 | 1.9 | 210 | 0.0354 | | 0.025 | 1.99 | 220 | 0.0269 | | 0.0297 | 2.08 | 230 | 0.0285 | | 0.0251 | 2.18 | 240 | 0.0250 | | 0.0203 | 2.27 | 250 | 0.0225 | | 0.0262 | 2.36 | 260 | 0.0242 | | 0.0211 | 2.45 | 270 | 0.0231 | | 0.0192 | 2.54 | 280 | 0.0225 | | 0.0239 | 2.63 | 290 | 0.0222 | | 0.0231 | 2.72 | 300 | 0.0221 | | 0.0214 | 2.81 | 310 | 0.0219 | | 0.0222 | 2.9 | 320 | 0.0218 | | 0.0248 | 2.99 | 330 | 0.0218 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1