v000000-syntheticmoist-1_2216

developer_uid: v000000

submission_id: v000000-syntheticmoist-1_2216_v1

model_name: v000000-syntheticmoist-1_2216_v1

model_group: v000000/SyntheticMoist-1

status: torndown

timestamp: 2024-06-12T18:54:57+00:00

num_battles: 7332

num_wins: 3309

celo_rating: 1165.38

family_friendly_score: 0.0

submission_type: basic

model_repo: v000000/SyntheticMoist-11B-v2-test01

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 10731524096.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: v000000-syntheticmoist-1_2216_v1

is_internal_developer: False

language_model: v000000/SyntheticMoist-11B-v2-test01

model_size: 11B

ranking_group: single

us_pacific_date: 2024-06-12

win_ratio: 0.4513093289689034

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

reward_formatter: {'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n'}

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name v000000-syntheticmoist-1-2216-v1-mkmlizer
Waiting for job on v000000-syntheticmoist-1-2216-v1-mkmlizer to finish
v000000-syntheticmoist-1-2216-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║     _____            __           __                                ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║       /___/                                                         ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║                                                                     ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║                                                                     ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  belonging to:                                                      ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║                                                                     ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ║                                                                     ║
v000000-syntheticmoist-1-2216-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-syntheticmoist-1-2216-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-syntheticmoist-1-2216-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-syntheticmoist-1-2216-v1-mkmlizer: Downloaded to shared memory in 46.923s
v000000-syntheticmoist-1-2216-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-syntheticmoist-1-2216-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-syntheticmoist-1-2216-v1-mkmlizer: quantized model in 19.528s
v000000-syntheticmoist-1-2216-v1-mkmlizer: Processed model v000000/SyntheticMoist-11B-v2-test01 in 69.850s
v000000-syntheticmoist-1-2216-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-syntheticmoist-1-2216-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-syntheticmoist-1-2216-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1/special_tokens_map.json
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1/tokenizer_config.json
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1/tokenizer.model
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1/config.json
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1/tokenizer.json
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-syntheticmoist-1-2216-v1/flywheel_model.0.safetensors
v000000-syntheticmoist-1-2216-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-syntheticmoist-1-2216-v1-mkmlizer: 
Loading 0:   0%|          | 0/435 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/435 [00:01<04:23,  1.64it/s]
Loading 0:   3%|▎         | 15/435 [00:01<00:27, 15.08it/s]
Loading 0:   8%|▊         | 33/435 [00:01<00:11, 36.08it/s]
Loading 0:  12%|█▏        | 51/435 [00:01<00:06, 57.27it/s]
Loading 0:  16%|█▌        | 69/435 [00:01<00:04, 78.28it/s]
Loading 0:  20%|██        | 87/435 [00:01<00:03, 97.43it/s]
Loading 0:  24%|██▎       | 103/435 [00:02<00:04, 72.00it/s]
Loading 0:  28%|██▊       | 121/435 [00:02<00:03, 89.45it/s]
Loading 0:  32%|███▏      | 139/435 [00:02<00:02, 105.38it/s]
Loading 0:  36%|███▌      | 157/435 [00:02<00:02, 119.53it/s]
Loading 0:  40%|████      | 175/435 [00:02<00:01, 131.70it/s]
Loading 0:  44%|████▍     | 193/435 [00:02<00:01, 141.39it/s]
Loading 0:  48%|████▊     | 210/435 [00:02<00:02, 90.78it/s] 
Loading 0:  52%|█████▏    | 225/435 [00:03<00:02, 101.11it/s]
Loading 0:  55%|█████▌    | 240/435 [00:03<00:01, 110.33it/s]
Loading 0:  59%|█████▉    | 258/435 [00:03<00:01, 123.55it/s]
Loading 0:  63%|██████▎   | 276/435 [00:03<00:01, 135.47it/s]
Loading 0:  67%|██████▋   | 293/435 [00:03<00:01, 140.13it/s]
Loading 0:  71%|███████   | 309/435 [00:03<00:01, 92.58it/s] 
Loading 0:  74%|███████▍  | 322/435 [00:03<00:01, 95.18it/s]
Loading 0:  78%|███████▊  | 339/435 [00:04<00:00, 109.57it/s]
Loading 0:  82%|████████▏ | 357/435 [00:04<00:00, 124.05it/s]
Loading 0:  86%|████████▌ | 375/435 [00:04<00:00, 134.30it/s]
Loading 0:  90%|█████████ | 393/435 [00:04<00:00, 143.95it/s]
Loading 0:  94%|█████████▍| 409/435 [00:04<00:00, 94.05it/s] 
Loading 0:  98%|█████████▊| 427/435 [00:04<00:00, 109.50it/s]
                                                             
/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-syntheticmoist-1-2216-v1-mkmlizer:   warnings.warn(
v000000-syntheticmoist-1-2216-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-syntheticmoist-1-2216-v1-mkmlizer:   warnings.warn(
v000000-syntheticmoist-1-2216-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-syntheticmoist-1-2216-v1-mkmlizer:   warnings.warn(
v000000-syntheticmoist-1-2216-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-syntheticmoist-1-2216-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-syntheticmoist-1-2216-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-syntheticmoist-1-2216-v1-mkmlizer: Saving duration: 0.427s
v000000-syntheticmoist-1-2216-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.598s
v000000-syntheticmoist-1-2216-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-syntheticmoist-1-2216-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-syntheticmoist-1-2216-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-syntheticmoist-1-2216-v1_reward/reward.tensors
Job v000000-syntheticmoist-1-2216-v1-mkmlizer completed after 103.68s with status: succeeded
Stopping job with name v000000-syntheticmoist-1-2216-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service v000000-syntheticmoist-1-2216-v1
Waiting for inference service v000000-syntheticmoist-1-2216-v1 to be ready
Inference service v000000-syntheticmoist-1-2216-v1 ready after 30.19194197654724s
Pipeline stage ISVCDeployer completed in 37.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6138107776641846s
Received healthy response to inference request in 1.422635555267334s
Received healthy response to inference request in 1.5511534214019775s
Received healthy response to inference request in 1.0824947357177734s
Received healthy response to inference request in 1.2234580516815186s
5 requests
0 failed requests
5th percentile: 1.1106873989105224
10th percentile: 1.1388800621032715
20th percentile: 1.1952653884887696
30th percentile: 1.2632935523986817
40th percentile: 1.3429645538330077
50th percentile: 1.422635555267334
60th percentile: 1.4740427017211915
70th percentile: 1.525449848175049
80th percentile: 1.763684892654419
90th percentile: 2.188747835159302
95th percentile: 2.401279306411743
99th percentile: 2.571304483413696
mean time: 1.5787105083465576
Pipeline stage StressChecker completed in 8.50s
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-syntheticmoist-1_2216_v1 status is now deployed due to DeploymentManager action
v000000-syntheticmoist-1_2216_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-syntheticmoist-1_2216_v1
Running pipeline stage ISVCDeleter
Checking if service v000000-syntheticmoist-1-2216-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.01s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-syntheticmoist-1-2216-v1/config.json from bucket guanaco-mkml-models
Deleting key v000000-syntheticmoist-1-2216-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-syntheticmoist-1-2216-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-syntheticmoist-1-2216-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-syntheticmoist-1-2216-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key v000000-syntheticmoist-1-2216-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-syntheticmoist-1-2216-v1_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-syntheticmoist-1-2216-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-syntheticmoist-1-2216-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-syntheticmoist-1-2216-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-syntheticmoist-1-2216-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-syntheticmoist-1-2216-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-syntheticmoist-1-2216-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.51s
v000000-syntheticmoist-1_2216_v1 status is now torndown due to DeploymentManager action