shisa-ai/shisa-v1-llama3-8b

Per the Llama 3 Community License Agreement, the official name of this model is "LLama 3 shisa-v1-llama3-8b"

8e6 moved in as it is a slightly superior model, will do some cleanup and renaming soon...

I ran the tests for 2 runs just to try to lower variance. These are all using temp 0.2, min_p 0.1, freq penalty 0.5

Model	AVG Score	ELYZA100	JA MT-Bench	Rakuda	Tengu-Bench	JA Char %
shisa-v1-llama3-8b.lr-2e4	3.97	4.60	4.54	3.33	3.42	92.42%
shisa-v1-llama3-8b.lr-5e5	5.73	6.28	6.45	5.37	4.81	90.93%
shisa-v1-llama3-8b.2e5	6.33	6.51	6.66	6.68	5.48	91.51%
shisa-v1-llama3-8b (8-e6)	6.59	6.67	6.95	7.05	5.68	91.30%
shisa-v1-llama3-8b.5e6	6.42	6.33	6.76	7.15	5.45	91.56%
shisa-v1-llama3-8b.2e6	6.31	6.26	6.88	6.73	5.38	92.00%

• The 2e-4 and 5e-5 are definitely overtrained and perform significantly worse.
• 2e-5 is on the edge since weightwacher shows the embed as slightly overtrained for 2e-5, but NEFTune version is not
• 8e-6 performs the best, and 5e-6 also performed slightly better than 2e-5

For a comparison of where it sits vs other models:

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
gpt-4o-2024-05-13	8.72	8.88	8.69	9.15	8.16
gemini-1.5-pro	8.58	8.58	8.93	9.20	7.61
claude-3-opus-20240229	8.55	8.64	8.58	8.75	8.23
CohereForAI/c4ai-command-r-plus	7.69	7.50	7.43	9.05	6.79
shisa-ai/shisa-v1-llama3-70b	7.30	7.34	7.67	8.15	6.04
gpt-3.5-turbo-0125	7.17	7.24	6.98	7.64	6.82
shisa-ai/shisa-v1-llama3-70b.2e5	7.17	7.16	7.45	7.98	6.09
karakuri-ai/karakuri-lm-8x7b-chat-v0.1	7.00	7.18	6.30	7.98	6.55
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	6.59	6.67	6.95	7.05	5.68
shisa-ai/shisa-swallowmx-13a47b-v1	6.17	6.48	6.07	7.11	5.03
lightblue/suzume-llama-3-8B-japanese	5.96	6.68	4.96	6.68	5.53
augmxnt/shisa-gamma-7b-v1	5.82	5.96	5.02	6.85	5.47
shisa-ai/shisa-v1-phi3-14b	5.77	6.28	5.26	6.55	5.01
shisa-ai/shisa-v1-gemma-8b	5.64	6.50	5.42	5.10	5.55
Rakuten/RakutenAI-7B-chat	5.58	5.92	4.60	6.58	5.24
lightblue/qarasu-14B-chat-plus-unleashed	5.20	5.58	4.74	5.46	5.01
shisa-ai/shisa-v1-mistral0.3-7b	5.11	5.64	6.10	3.83	4.86
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
augmxnt/shisa-7b-v1	4.50	4.63	3.95	4.89	4.53

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

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/lr-8e6

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: shisa-v1-llama3-8b.lr-8e6

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: linear
learning_rate: 8e-6

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 0
debug:
deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.00
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

outputs/lr-8e6

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4983

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: 8e-06
• 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: 100
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.3951	0.0064	1	0.8645
0.8731	0.5020	79	0.5577
0.8405	1.0040	158	0.5138
0.6888	1.4853	237	0.4982
0.6674	1.9873	316	0.4870
0.5859	2.4694	395	0.4983

Framework versions

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