shisa-ai/shisa-v1-llama3-70b.2e5

shisa-v2 Base Model ablation

The 8e-6 version is better and you should probably use that one.

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
gpt-3.5-turbo-0125	7.17	7.24	6.98	7.64	6.82
shisa-ai/shisa-v1-llama3-70b	7.17	7.16	7.45	7.98	6.09
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-v1-llama3-8b^	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
shisa-ai/shisa-v1-llama3-8b	6.10	6.52	6.20	6.37	5.33
Rakuten/RakutenAI-7B-chat	5.58	5.92	4.60	6.58	5.24
shisa-ai/shisa-v1-gemma-8b	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-v1-yi1.5-9b	4.63	5.98	4.28	3.26	5.00

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-70B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

hub_model_id: shisa-ai/shisa-llama3-70b-v1
hub_strategy: end

use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: shisa-llama3-70b-v1

chat_template: llama3
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-llama3-70b

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 3
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
gradient_checkpointing_kwargs:
  use_reentrant: false
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: 0
debug:
deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

shisa-llama3-70b-v1

This model is a fine-tuned version of meta-llama/Meta-Llama-3-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4425

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
• distributed_type: multi-GPU
• num_devices: 16
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 87
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.2478	0.0033	1	0.7102
0.7516	0.5008	154	0.4325
0.7185	1.0016	308	0.3966
0.3708	1.4862	462	0.3976
0.3758	1.9870	616	0.3840
0.0928	2.4699	770	0.4425

Framework versions

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