|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl-sft |
|
- generated_from_trainer |
|
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T |
|
model-index: |
|
- name: tinyllama_lora_adcopy |
|
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. --> |
|
|
|
# tinyllama_lora_adcopy |
|
|
|
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8992 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.9386 | 1.0 | 129 | 0.8662 | |
|
| 0.7821 | 2.0 | 258 | 0.7954 | |
|
| 0.5269 | 3.0 | 387 | 0.7621 | |
|
| 0.4121 | 4.0 | 516 | 0.7183 | |
|
| 0.2169 | 5.0 | 645 | 0.7358 | |
|
| 0.1206 | 6.0 | 774 | 0.7757 | |
|
| 0.057 | 7.0 | 903 | 0.8003 | |
|
| 0.0291 | 8.0 | 1032 | 0.8342 | |
|
| 0.0097 | 9.0 | 1161 | 0.8800 | |
|
| 0.0077 | 10.0 | 1290 | 0.8992 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
