---
library_name: transformers
license: apache-2.0
base_model: kakaocorp/kanana-1.5-2.1b-instruct-2505
tags:
- axolotl
- generated_from_trainer
datasets:
- train.jsonl
model-index:
- name: fc-reasoning-2.1b
  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: `0.12.2`
```yaml
base_model: kakaocorp/kanana-1.5-2.1b-instruct-2505


load_in_8bit: false
load_in_4bit: false

datasets:
  - path: train.jsonl
    type: chat_template

dataset_prepared_path: preprocess
val_set_size: 0.01
output_dir: ./outputs
dataloader_num_workers: 56

adapter: 
lora_model_dir:

sequence_len: 16384
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: false

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

wandb_project: fastcampus
wandb_entity: guijinson
wandb_watch:
wandb_name: fc-proj2-reasoning-2.1b
wandb_log_model:
hub_model_id: amphora/fc-reasoning-2.1b

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5

bf16: auto
tf32: false

gradient_checkpointing:
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.05
weight_decay: 0.01
evals_per_epoch: 0
saves_per_epoch: 1

```

</details><br>

# fc-reasoning-2.1b

This model is a fine-tuned version of [kakaocorp/kanana-1.5-2.1b-instruct-2505](https://huggingface.co/kakaocorp/kanana-1.5-2.1b-instruct-2505) on the train.jsonl dataset.

## 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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 64
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 53
- training_steps: 1072

### Training results



### Framework versions

- Transformers 4.55.2
- Pytorch 2.6.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4