submission_id: cycy233-misllm-v6-9-7_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.9.7
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, '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: 2024-06-14T06:44:19+00:00
model_name: cycy233-misllm-v6-9-7_v1
model_eval_status: success
model_group: cycy233/misllm_v6.9.7
num_battles: 21629
num_wins: 10318
celo_rating: 1167.15
propriety_score: 0.6795454545454546
propriety_total_count: 9680.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-misllm-v6-9-7_v1
ineligible_reason: None
language_model: cycy233/misllm_v6.9.7
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-13
win_ratio: 0.47704470849322667
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-9-7-v1-mkmlizer
Waiting for job on cycy233-misllm-v6-9-7-v1-mkmlizer to finish
cycy233-misllm-v6-9-7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-9-7-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.
cycy233-misllm-v6-9-7-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-9-7-v1-mkmlizer: Downloaded to shared memory in 43.097s
cycy233-misllm-v6-9-7-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-7-v1-mkmlizer: quantized model in 15.379s
cycy233-misllm-v6-9-7-v1-mkmlizer: Processed model cycy233/misllm_v6.9.7 in 60.793s
cycy233-misllm-v6-9-7-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1/config.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1/tokenizer_config.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1/special_tokens_map.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1/tokenizer.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1/tokenizer.model
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-v1/flywheel_model.0.safetensors
cycy233-misllm-v6-9-7-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-7-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.
cycy233-misllm-v6-9-7-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-7-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.
cycy233-misllm-v6-9-7-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-7-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.
cycy233-misllm-v6-9-7-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-7-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()
cycy233-misllm-v6-9-7-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-9-7-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-9-7-v1-mkmlizer: Saving duration: 0.386s
cycy233-misllm-v6-9-7-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 17.063s
cycy233-misllm-v6-9-7-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-9-7-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-9-7-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/config.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/special_tokens_map.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/tokenizer_config.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/merges.txt
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/vocab.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/tokenizer.json
cycy233-misllm-v6-9-7-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-9-7-v1_reward/reward.tensors
Job cycy233-misllm-v6-9-7-v1-mkmlizer completed after 103.38s with status: succeeded
Stopping job with name cycy233-misllm-v6-9-7-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-9-7-v1
Waiting for inference service cycy233-misllm-v6-9-7-v1 to be ready
Inference service cycy233-misllm-v6-9-7-v1 ready after 40.245720624923706s
Pipeline stage ISVCDeployer completed in 47.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0823347568511963s
Received healthy response to inference request in 1.193420648574829s
Received healthy response to inference request in 1.1762621402740479s
Received healthy response to inference request in 1.115156888961792s
Received healthy response to inference request in 1.1709957122802734s
5 requests
0 failed requests
5th percentile: 1.1263246536254883
10th percentile: 1.1374924182891846
20th percentile: 1.1598279476165771
30th percentile: 1.1720489978790283
40th percentile: 1.1741555690765382
50th percentile: 1.1762621402740479
60th percentile: 1.1831255435943604
70th percentile: 1.189988946914673
80th percentile: 1.3712034702301028
90th percentile: 1.7267691135406495
95th percentile: 1.9045519351959226
99th percentile: 2.0467781925201414
mean time: 1.3476340293884277
Pipeline stage StressChecker completed in 7.34s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v6-9-7_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-9-7_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics