metadata
base_model: NowaBwagel0/llama-68m-oasst
license: other
tags:
- generated_from_trainer
model-index:
- name: llama-68m-oasst
results: []
llama-68m-oasst
This model is a fine-tuned version of NowaBwagel0/llama-68m-oasst on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6231
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.197 | 0.9987 | 382 | 2.5801 |
| 2.1256 | 2.0 | 765 | 2.5814 |
| 2.0953 | 2.9987 | 1147 | 2.5903 |
| 2.1023 | 4.0 | 1530 | 2.5968 |
| 2.0331 | 4.9987 | 1912 | 2.6012 |
| 2.0151 | 6.0 | 2295 | 2.6076 |
| 1.9609 | 6.9987 | 2677 | 2.6150 |
| 1.9311 | 8.0 | 3060 | 2.6203 |
| 1.9812 | 8.9882 | 3438 | 2.6231 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1