metadata
library_name: peft
license: apache-2.0
base_model: allenai/OLMo-7B-0724-hf
tags:
- generated_from_trainer
model-index:
- name: simplewiki_baseline
results: []
simplewiki_baseline
This model is a fine-tuned version of allenai/OLMo-7B-0724-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3323
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: 0.002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3175 | 0.5378 | 20 | 2.3252 |
| 2.3075 | 1.0538 | 40 | 2.2998 |
| 2.2741 | 1.5916 | 60 | 2.3083 |
| 2.2257 | 2.1076 | 80 | 2.3041 |
| 2.2605 | 2.6454 | 100 | 2.3115 |
Framework versions
- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.6.0
- Datasets 3.3.2
- Tokenizers 0.21.0