Hugging Face's logo

shisa-ai
/
shisa-v1-swallowmx-13a47b

Text Generation
Transformers
Safetensors
Japanese
English
mixtral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
shisa-v1-swallowmx-13a47b / README.md
leonardlin's picture
leonardlin
Update README.md
c601b4e verified
preview code
|
raw
history blame
5.33 kB
metadata
license: apache-2.0
language:
  - ja
  - en
datasets:
  - augmxnt/ultra-orca-boros-en-ja-v1
base_model: tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
tags:
  - generated_from_trainer

shisa-v2 Base Model ablation

Using a fork of Lightblue's Shaberi benchmark framework:

Model Average ELYZA-tasks-100 MT-Bench Rakuda Tengu-Bench
gpt-4-turbo-2024-04-09 8.75 8.78 8.74 9.18 8.31
CohereForAI/c4ai-command-r-plus 7.69 7.50 7.43 9.05 6.79
karakuri-ai/karakuri-lm-70b-chat-v0.1 6.84 6.86 6.43 7.85 6.23
lightblue/ao-karasu-72B 6.81 7.19 6.54 7.25 6.27
shisa-ai/shisa-llama3-8b-v1^ 6.29 6.62 6.41 7.05 5.07
shisa-ai/shisa-swallowmx-13a47b-v1^ 6.17 6.48 6.07 7.11 5.03
Rakuten/RakutenAI-7B-chat 5.58 5.92 4.60 6.58 5.24
shisa-ai/shisa-gemma-7b-v1 5.64 6.50 5.42 5.10 5.55
augmxnt/shisa-gamma-7b-v1 5.56 5.84 4.00 6.73 5.68
lightblue/qarasu-14B-chat-plus-unleashed 5.20 5.58 4.74 5.46 5.01
cyberagent/calm2-7b-chat 4.76 4.90 3.58 5.75 4.81
mistralai/Mistral-7B-Instruct-v0.2 4.69 5.78 4.65 3.80 4.53
shisa-ai/shisa-yi1.5-9b-v1 4.63 5.98 4.28 3.26 5.00

^ Sampler settings: temperature 0.2, min_p 0.1, frequency_penalty 0.5

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: inst
datasets:
  - path: augmxnt/ultra-orca-boros-en-ja-v1
    type: sharegpt
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/basemodel-swallowmx-8x22b

model_config:
  output_router_logits: true

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: shisa-swallowmx-13a47b-v1

global_batch_size: 1
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
# https://github.com/huggingface/transformers/issues/22101
# https://github.com/huggingface/transformers/blob/main/src/transformers/training_args.py#L141
optimizer: paged_adamw_8bit
lr_scheduler: linear
learning_rate: 2e-5

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

outputs/basemodel-swallowmx-8x22b

This model is a fine-tuned version of tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4443

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: 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=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 119
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.5705 0.0022 1 0.5065
0.505 0.4993 229 0.3910
0.5258 0.9986 458 0.3654
0.2964 1.4835 687 0.3786
0.2923 1.9828 916 0.3669
0.1462 2.4682 1145 0.4429
0.1156 2.9676 1374 0.4443

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1