submission_id: v000000-l3-8b-poppy-suns_2519_v1
developer_uid: v000000
status: inactive
model_repo: v000000/L3-8B-Poppy-Sunspice-experiment-d
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-06-06T11:58:17+00:00
model_name: v000000-l3-8b-poppy-suns_2519_v1
model_eval_status: success
model_group: v000000/L3-8B-Poppy-Suns
num_battles: 7642
num_wins: 4059
celo_rating: 1203.44
safety_score: 0.93
propriety_score: 0.678391959798995
propriety_total_count: 398.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: v000000-l3-8b-poppy-suns_2519_v1
ineligible_reason: propriety_total_count < 5000
language_model: v000000/L3-8B-Poppy-Sunspice-experiment-d
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5311436796650092
Resubmit model
Running pipeline stage MKMLizer
Starting job with name v000000-l3-8b-poppy-suns-2519-v1-mkmlizer
Waiting for job on v000000-l3-8b-poppy-suns-2519-v1-mkmlizer to finish
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ _____ __ __ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ /___/ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ Version: 0.8.14 ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ https://mk1.ai ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ The license key for the current software has been verified as ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ belonging to: ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ Chai Research Corp. ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ║ ║
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Downloaded to shared memory in 38.601s
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:42, 2.02s/it] Loading 0: 7%|▋ | 19/291 [00:04<00:43, 6.29it/s] Loading 0: 14%|█▎ | 40/291 [00:04<00:15, 15.75it/s] Loading 0: 20%|██ | 59/291 [00:04<00:08, 26.51it/s] Loading 0: 26%|██▌ | 75/291 [00:04<00:07, 29.73it/s] Loading 0: 32%|███▏ | 94/291 [00:04<00:04, 42.97it/s] Loading 0: 39%|███▉ | 113/291 [00:04<00:03, 58.31it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:02, 74.85it/s] Loading 0: 52%|█████▏ | 152/291 [00:05<00:01, 94.52it/s] Loading 0: 58%|█████▊ | 170/291 [00:05<00:01, 71.00it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:01, 92.99it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:00, 109.36it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 133.40it/s] Loading 0: 88%|████████▊ | 257/291 [00:06<00:00, 144.92it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 95.16it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: quantized model in 17.492s
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-2519-v1
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-2519-v1/config.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-2519-v1/special_tokens_map.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-2519-v1/tokenizer_config.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-2519-v1/tokenizer.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-poppy-suns-2519-v1/flywheel_model.0.safetensors
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: warnings.warn(
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: return self.fget.__get__(instance, owner)()
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Saving duration: 0.268s
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.302s
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/special_tokens_map.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/config.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/tokenizer_config.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/vocab.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/merges.txt
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/tokenizer.json
v000000-l3-8b-poppy-suns-2519-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-poppy-suns-2519-v1_reward/reward.tensors
Job v000000-l3-8b-poppy-suns-2519-v1-mkmlizer completed after 85.03s with status: succeeded
Stopping job with name v000000-l3-8b-poppy-suns-2519-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-poppy-suns-2519-v1
Waiting for inference service v000000-l3-8b-poppy-suns-2519-v1 to be ready
Inference service v000000-l3-8b-poppy-suns-2519-v1 ready after 30.42374038696289s
Pipeline stage ISVCDeployer completed in 38.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1149990558624268s
Received healthy response to inference request in 1.157944917678833s
Received healthy response to inference request in 1.171550989151001s
Received healthy response to inference request in 1.2083404064178467s
Received healthy response to inference request in 1.166656732559204s
5 requests
0 failed requests
5th percentile: 1.1596872806549072
10th percentile: 1.1614296436309814
20th percentile: 1.1649143695831299
30th percentile: 1.1676355838775634
40th percentile: 1.1695932865142822
50th percentile: 1.171550989151001
60th percentile: 1.1862667560577393
70th percentile: 1.2009825229644775
80th percentile: 1.3896721363067628
90th percentile: 1.7523355960845948
95th percentile: 1.9336673259735107
99th percentile: 2.0787327098846435
mean time: 1.3638984203338622
Pipeline stage StressChecker completed in 7.42s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
v000000-l3-8b-poppy-suns_2519_v1 status is now deployed due to DeploymentManager action
v000000-l3-8b-poppy-suns_2519_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics