|
--- |
|
license: apache-2.0 |
|
base_model: allenai/OLMo-1B |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: O0430HMA11 |
|
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. --> |
|
|
|
# O0430HMA11 |
|
|
|
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: 0.0488 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.8065 | 0.09 | 10 | 0.2263 | |
|
| 0.1808 | 0.18 | 20 | 0.1533 | |
|
| 0.1504 | 0.27 | 30 | 0.1703 | |
|
| 0.1539 | 0.36 | 40 | 0.1510 | |
|
| 0.1512 | 0.45 | 50 | 0.1499 | |
|
| 0.1501 | 0.54 | 60 | 0.1405 | |
|
| 0.147 | 0.63 | 70 | 0.1753 | |
|
| 0.1464 | 0.73 | 80 | 0.1267 | |
|
| 0.0872 | 0.82 | 90 | 0.0932 | |
|
| 0.0774 | 0.91 | 100 | 0.0758 | |
|
| 0.2628 | 1.0 | 110 | 1.3590 | |
|
| 2.7529 | 1.09 | 120 | 1.8422 | |
|
| 0.9754 | 1.18 | 130 | 0.4673 | |
|
| 0.4054 | 1.27 | 140 | 0.3541 | |
|
| 0.3357 | 1.36 | 150 | 0.2889 | |
|
| 0.1804 | 1.45 | 160 | 0.1196 | |
|
| 0.1405 | 1.54 | 170 | 0.1951 | |
|
| 0.167 | 1.63 | 180 | 0.0872 | |
|
| 0.0958 | 1.72 | 190 | 0.0867 | |
|
| 0.0841 | 1.81 | 200 | 0.0904 | |
|
| 0.0816 | 1.9 | 210 | 0.0862 | |
|
| 0.0803 | 1.99 | 220 | 0.0776 | |
|
| 0.0764 | 2.08 | 230 | 0.0763 | |
|
| 0.0722 | 2.18 | 240 | 0.0770 | |
|
| 0.0699 | 2.27 | 250 | 0.0731 | |
|
| 0.0702 | 2.36 | 260 | 0.0677 | |
|
| 0.0624 | 2.45 | 270 | 0.0621 | |
|
| 0.0539 | 2.54 | 280 | 0.0573 | |
|
| 0.054 | 2.63 | 290 | 0.0551 | |
|
| 0.0542 | 2.72 | 300 | 0.0513 | |
|
| 0.0495 | 2.81 | 310 | 0.0492 | |
|
| 0.0485 | 2.9 | 320 | 0.0494 | |
|
| 0.0497 | 2.99 | 330 | 0.0488 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
