metadata
license: other
base_model: NowaBwagel0/llama-68m-oasst
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: 3.8987
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: 18
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.97 | 0.9987 | 382 | 3.4996 |
| 0.9273 | 2.0 | 765 | 3.5370 |
| 0.9176 | 2.9987 | 1147 | 3.5715 |
| 0.9004 | 4.0 | 1530 | 3.6086 |
| 0.8736 | 4.9987 | 1912 | 3.6379 |
| 0.8599 | 6.0 | 2295 | 3.6761 |
| 0.7955 | 6.9987 | 2677 | 3.7044 |
| 0.7741 | 8.0 | 3060 | 3.7346 |
| 0.7364 | 8.9987 | 3442 | 3.7615 |
| 0.7605 | 10.0 | 3825 | 3.7855 |
| 0.695 | 10.9987 | 4207 | 3.8088 |
| 0.7111 | 12.0 | 4590 | 3.8332 |
| 0.6849 | 12.9987 | 4972 | 3.8490 |
| 0.6862 | 14.0 | 5355 | 3.8659 |
| 0.6834 | 14.9987 | 5737 | 3.8785 |
| 0.6541 | 16.0 | 6120 | 3.8898 |
| 0.646 | 16.9987 | 6502 | 3.8961 |
| 0.6777 | 17.9765 | 6876 | 3.8987 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1