---
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: google/gemma-2b-it
model-index:
- name: peft-gemma2b
  results: []
---


[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.0`
```yaml
# use google/gemma-7b if you have access
base_model: google/gemma-2b-it
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

# huggingface repo
datasets:
  - path: ./python-oasst/combined_chunk_2.jsonl
    type: oasst
val_set_size: 0.40
output_dir: ./out3

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: gemma-2b-it
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:


gradient_accumulation_steps: 3
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: true
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 256
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

```

</details><br>

# out3

This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2430

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 3
- total_train_batch_size: 48
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8926        | 0.02  | 1    | 2.7617          |
| 1.4502        | 0.26  | 12   | 1.4564          |
| 1.7617        | 0.52  | 24   | 1.3147          |
| 1.2051        | 0.78  | 36   | 1.2781          |
| 1.1353        | 1.01  | 48   | 1.2603          |
| 1.1787        | 1.28  | 60   | 1.2498          |
| 1.1416        | 1.54  | 72   | 1.2445          |
| 1.1606        | 1.8   | 84   | 1.2430          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.0
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.15.0