submission_id: chaoticneutrals-poppy-po_3816_v2
developer_uid: chai_backend_admin
status: torndown
model_repo: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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: 2024-05-11T00:29:03+00:00
model_name: chaoticneutrals-poppy-po_3816_v2
model_eval_status: success
model_group: ChaoticNeutrals/Poppy_Po
num_battles: 35856
num_wins: 19768
celo_rating: 1204.14
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaoticneutrals-poppy-po_3816_v2
ineligible_reason: propriety_total_count < 800
language_model: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-10
win_ratio: 0.5513163766175815
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaoticneutrals-poppy-po-3816-v2-mkmlizer
Waiting for job on chaoticneutrals-poppy-po-3816-v2-mkmlizer to finish
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ _____ __ __ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ /___/ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ Version: 0.8.10 ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ belonging to: ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ Chai Research Corp. ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaoticneutrals-poppy-po-3816-v2-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.
chaoticneutrals-poppy-po-3816-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Downloaded to shared memory in 50.450s
chaoticneutrals-poppy-po-3816-v2-mkmlizer: quantizing model to /dev/shm/model_cache
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:07, 23.59it/s] Loading 0: 77%|███████▋ | 223/291 [00:11<00:03, 19.40it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaoticneutrals-poppy-po-3816-v2-mkmlizer: quantized model in 18.047s
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Processed model ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B in 69.588s
chaoticneutrals-poppy-po-3816-v2-mkmlizer: creating bucket guanaco-mkml-models
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaoticneutrals-poppy-po-3816-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v2
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v2/config.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v2/special_tokens_map.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v2/tokenizer_config.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v2/tokenizer.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v2/flywheel_model.0.safetensors
chaoticneutrals-poppy-po-3816-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaoticneutrals-poppy-po-3816-v2-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.
chaoticneutrals-poppy-po-3816-v2-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-v2-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.
chaoticneutrals-poppy-po-3816-v2-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-v2-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()
chaoticneutrals-poppy-po-3816-v2-mkmlizer: return self.fget.__get__(instance, owner)()
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Saving duration: 0.238s
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 11.382s
chaoticneutrals-poppy-po-3816-v2-mkmlizer: creating bucket guanaco-reward-models
chaoticneutrals-poppy-po-3816-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaoticneutrals-poppy-po-3816-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/special_tokens_map.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/config.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/tokenizer_config.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/merges.txt
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/vocab.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/tokenizer.json
chaoticneutrals-poppy-po-3816-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v2_reward/reward.tensors
Job chaoticneutrals-poppy-po-3816-v2-mkmlizer completed after 112.28s with status: succeeded
Stopping job with name chaoticneutrals-poppy-po-3816-v2-mkmlizer
Pipeline stage MKMLizer completed in 113.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.42s
Running pipeline stage ISVCDeployer
Creating inference service chaoticneutrals-poppy-po-3816-v2
Waiting for inference service chaoticneutrals-poppy-po-3816-v2 to be ready
Inference service chaoticneutrals-poppy-po-3816-v2 ready after 30.566757917404175s
Pipeline stage ISVCDeployer completed in 31.99s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.6651337146759033s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.4575600624084473s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.727865219116211s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.4416933059692383s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.6523587703704834s
5 requests
0 failed requests
5th percentile: 1.667460060119629
10th percentile: 1.6825613498687744
20th percentile: 1.7127639293670653
30th percentile: 1.8706308364868165
40th percentile: 2.156162071228027
50th percentile: 2.4416933059692383
60th percentile: 2.448040008544922
70th percentile: 2.4543867111206055
80th percentile: 2.4990747928619386
90th percentile: 2.5821042537689207
95th percentile: 2.623618984222412
99th percentile: 2.656830768585205
mean time: 2.1889222145080565
Pipeline stage StressChecker completed in 14.51s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.17s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.15s
%s, retrying in %s seconds...
Running M-Eval for topic stay_in_character
chaoticneutrals-poppy-po_3816_v2 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
chaoticneutrals-poppy-po_3816_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaoticneutrals-poppy-po_3816_v2
Running pipeline stage ISVCDeleter
Checking if service chaoticneutrals-poppy-po-3816-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaoticneutrals-poppy-po-3816-v2/config.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.10s
chaoticneutrals-poppy-po_3816_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics