---
library_name: peft
license: gemma
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 5402150b-2c7a-4580-afd0-dee4ebb62789
  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. -->

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

axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - df63738bce474e71_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/df63738bce474e71_train_data.json
  type:
    field_input: description_left
    field_instruction: category_left
    field_output: title_left
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: filipesantoscv11/5402150b-2c7a-4580-afd0-dee4ebb62789
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 79GiB
max_steps: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/df63738bce474e71_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 479d98b7-ca6f-47b6-8cdf-cdb89063f20b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 479d98b7-ca6f-47b6-8cdf-cdb89063f20b
warmup_steps: 10
weight_decay: 0.01
xformers_attention: true

```

</details><br>

# 5402150b-2c7a-4580-afd0-dee4ebb62789

This model is a fine-tuned version of [zake7749/gemma-2-2b-it-chinese-kyara-dpo](https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4035

## 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 30

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0.0009 | 1    | 4.2219          |
| 3.7731        | 0.0047 | 5    | 3.8616          |
| 3.449         | 0.0094 | 10   | 2.9449          |
| 2.8162        | 0.0140 | 15   | 2.6583          |
| 2.3992        | 0.0187 | 20   | 2.4839          |
| 2.4648        | 0.0234 | 25   | 2.4180          |
| 2.3158        | 0.0281 | 30   | 2.4035          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1