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: 4.1198
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 |
|---|---|---|---|
| 0.7089 | 0.9987 | 382 | 3.9090 |
| 0.6716 | 2.0 | 765 | 3.9535 |
| 0.6583 | 2.9987 | 1147 | 3.9890 |
| 0.6402 | 4.0 | 1530 | 4.0211 |
| 0.6224 | 4.9987 | 1912 | 4.0493 |
| 0.6119 | 6.0 | 2295 | 4.0758 |
| 0.558 | 6.9987 | 2677 | 4.0987 |
| 0.5383 | 8.0 | 3060 | 4.1135 |
| 0.5506 | 8.9882 | 3438 | 4.1198 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1