|
--- |
|
license: gemma |
|
base_model: google/gemma-2-2b |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: gemma-2-2b_hs2_iter1_sftsd1 |
|
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. --> |
|
|
|
# gemma-2-2b_hs2_iter1_sftsd1 |
|
|
|
This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1432 |
|
- Num Input Tokens Seen: 2292888 |
|
|
|
## 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: 8e-06 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 16 |
|
- seed: 1 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:| |
|
| No log | 0 | 0 | 1.3956 | 0 | |
|
| 1.1944 | 0.128 | 5 | 1.2251 | 296424 | |
|
| 1.0856 | 0.256 | 10 | 1.1691 | 586064 | |
|
| 0.9425 | 0.384 | 15 | 1.1694 | 882936 | |
|
| 0.8999 | 0.512 | 20 | 1.1552 | 1175128 | |
|
| 0.7419 | 0.64 | 25 | 1.1657 | 1472096 | |
|
| 0.6033 | 0.768 | 30 | 1.1648 | 1766904 | |
|
| 0.5839 | 0.896 | 35 | 1.1551 | 2059616 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
