---
library_name: transformers
license: other
base_model: LiquidAI/LFM2-350M-ENJP-MT
tags:
- generated_from_trainer
datasets:
- chotto-20251010.sft.jsonl
model-index:
- name: data/outputs/shisa-v2.1c-lfm2-350m-sft2
  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: `0.13.0.dev0`
```yaml
base_model: LiquidAI/LFM2-350M-ENJP-MT

chunked_cross_entropy: true

eot_tokens:
  - "<|im_end|>"
datasets:
  - path: chotto-20251010.sft.jsonl
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      assistant:
        - assistant
        - gpt
        - model
      user:
        - user
        - human
    roles_to_train: ["assistant"]
dataset_prepared_path: last_run_prepared_sft
output_dir: /data/outputs/shisa-v2.1c-lfm2-350m-sft2

sequence_len: 8192
sample_packing: true
flash_attention: true
pad_to_sequence_len: true

neftune_noise_alpha: 5

use_wandb: true
wandb_entity: augmxnt
wandb_project: liquid-hackathon-tokyo
wandb_name: "shisa-v2.1c-lfm2-350m-sft2"

# GBS = 128 / 8 GPU / 16 MBS / 1 GAS
gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 4
optimizer: adamw_torch_4bit
lr_scheduler: cosine
learning_rate: 6e-5 # 4.78 @ GBS=128

train_on_inputs: false
group_by_length: false
bf16: true
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
logging_steps: 1

warmup_ratio: 0.03
saves_per_epoch: 1

deepspeed: zero3_bf16.json
weight_decay: 1e-4

```

</details><br>

# data/outputs/shisa-v2.1c-lfm2-350m-sft2

This model is a fine-tuned version of [LiquidAI/LFM2-350M-ENJP-MT](https://huggingface.co/LiquidAI/LFM2-350M-ENJP-MT) on the chotto-20251010.sft.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: 6e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_4BIT 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: 69
- training_steps: 2332

### Training results



### Framework versions

- Transformers 4.57.0
- Pytorch 2.8.0+rocm6.4
- Datasets 4.1.1
- Tokenizers 0.22.1