---
library_name: peft
base_model: Korabbit/llama-2-ko-7b
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3fffc2ba-721b-4f7b-b7d8-73b9eaff22fc
  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: Korabbit/llama-2-ko-7b
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 9a7478f7dc0c77a4_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/9a7478f7dc0c77a4_train_data.json
  type:
    field_input: dense_caption
    field_instruction: video_id
    field_output: short_caption
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: sn56a1/3fffc2ba-721b-4f7b-b7d8-73b9eaff22fc
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: 1
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: 77GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/9a7478f7dc0c77a4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
save_strategy: steps
sequence_len: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: null
wandb_project: god
wandb_run: 1rv6
wandb_runid: null
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

```

</details><br>

# 3fffc2ba-721b-4f7b-b7d8-73b9eaff22fc

This model is a fine-tuned version of [Korabbit/llama-2-ko-7b](https://huggingface.co/Korabbit/llama-2-ko-7b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3648

## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- 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: 100

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.4707        | 0.0001 | 1    | 1.5667          |
| 1.1425        | 0.0013 | 9    | 1.0525          |
| 0.7161        | 0.0026 | 18   | 0.5472          |
| 0.4155        | 0.0038 | 27   | 0.4718          |
| 0.3661        | 0.0051 | 36   | 0.4287          |
| 0.4127        | 0.0064 | 45   | 0.4043          |
| 0.4001        | 0.0077 | 54   | 0.3882          |
| 0.3251        | 0.0089 | 63   | 0.3773          |
| 0.3656        | 0.0102 | 72   | 0.3719          |
| 0.295         | 0.0115 | 81   | 0.3674          |
| 0.4267        | 0.0128 | 90   | 0.3652          |
| 0.3669        | 0.0140 | 99   | 0.3648          |


### Framework versions

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