|
--- |
|
license: gemma |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: google/gemma-2b |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: Not-so-bright-AGI-v1 |
|
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. --> |
|
|
|
# Not-so-bright-AGI-v1 |
|
|
|
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0209 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- training_steps: 1480 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 2.9261 | 1.6393 | 100 | 2.5691 | |
|
| 2.4363 | 3.2787 | 200 | 2.2789 | |
|
| 2.2448 | 4.9180 | 300 | 2.1604 | |
|
| 2.1502 | 6.5574 | 400 | 2.1008 | |
|
| 2.111 | 8.1967 | 500 | 2.0725 | |
|
| 2.0837 | 9.8361 | 600 | 2.0565 | |
|
| 2.0646 | 11.4754 | 700 | 2.0456 | |
|
| 2.0499 | 13.1148 | 800 | 2.0378 | |
|
| 2.0497 | 14.7541 | 900 | 2.0323 | |
|
| 2.0275 | 16.3934 | 1000 | 2.0282 | |
|
| 2.0271 | 18.0328 | 1100 | 2.0255 | |
|
| 2.0205 | 19.6721 | 1200 | 2.0233 | |
|
| 2.0218 | 21.3115 | 1300 | 2.0219 | |
|
| 2.011 | 22.9508 | 1400 | 2.0209 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.0 |
|
- Pytorch 2.0.1a0+cxx11.abi |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
