|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Llama-2-7B-fp16 |
|
model-index: |
|
- name: Saiga_timelist_task30steps |
|
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. --> |
|
|
|
# Saiga_timelist_task30steps |
|
|
|
This model is a fine-tuned version of [TheBloke/Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0384 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 10 |
|
- total_train_batch_size: 20 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2298 | 0.37 | 2 | 2.2027 | |
|
| 2.0986 | 0.74 | 4 | 2.1505 | |
|
| 2.0278 | 1.11 | 6 | 2.1167 | |
|
| 1.9954 | 1.48 | 8 | 2.0915 | |
|
| 1.9696 | 1.85 | 10 | 2.0753 | |
|
| 1.8978 | 2.22 | 12 | 2.0648 | |
|
| 1.9246 | 2.59 | 14 | 2.0564 | |
|
| 1.9361 | 2.96 | 16 | 2.0506 | |
|
| 1.895 | 3.33 | 18 | 2.0470 | |
|
| 1.8525 | 3.7 | 20 | 2.0442 | |
|
| 1.8912 | 4.07 | 22 | 2.0419 | |
|
| 1.8689 | 4.44 | 24 | 2.0400 | |
|
| 1.9054 | 4.81 | 26 | 2.0390 | |
|
| 1.8537 | 5.19 | 28 | 2.0384 | |
|
| 1.8501 | 5.56 | 30 | 2.0384 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
