---
license: cc-by-nc-4.0
base_model: CohereForAI/c4ai-command-r-v01
tags:
- axolotl
- generated_from_trainer
model-index:
- name: command-r-ja-sharegpt
  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/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
base_model: CohereForAI/c4ai-command-r-v01

load_in_8bit: false
load_in_4bit: false
strict: false

hub_model_id: yentinglin/command-r-ja-sharegpt
hub_strategy: end

datasets:
  - path: NTQAI/sharegpt-clean-ja
    type: sharegpt
    conversation: chatml

chat_template: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./output/ja/sft/command-r/sharegpt/

sequence_len: 4096
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: JA-LLM
wandb_entity:
wandb_watch:
wandb_name: sft-fft-command-r-sharegpt-clean-ja
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1 # decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of peak lr
learning_rate: 1e-5
adam_beta1: 0.9
adam_beta2: 0.95
adam_eps: 0.00001
max_grad_norm: 1.0

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 5
xformers_attention:
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true

warmup_ratio: 0.02  # cannot use with warmup_steps
evals_per_epoch: 1
eval_table_size:
save_per_epoch: 1
save_total_limit: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16.json # multi-gpu only
weight_decay: 0.001
fsdp:
fsdp_config:
special_tokens:

ddp_timeout: 180000

special_tokens:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"

```

</details><br>

# command-r-ja-sharegpt

This model is a fine-tuned version of [CohereForAI/c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01) on the None 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 4

### Training results



### Framework versions

- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.0