submission_id: cycy233-misllm-v9-0-1_v11
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v9.0.1
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': True}
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': True}
timestamp: 2024-06-19T08:46:24+00:00
model_name: base
model_group: cycy233/misllm_v9.0.1
num_battles: 21194
num_wins: 11168
celo_rating: 1190.24
propriety_score: 0.698713690440244
propriety_total_count: 16559.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
ineligible_reason: None
language_model: cycy233/misllm_v9.0.1
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.5269415872416722
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v9-0-1-v11-mkmlizer
Waiting for job on cycy233-misllm-v9-0-1-v11-mkmlizer to finish
cycy233-misllm-v9-0-1-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ /___/ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ belonging to: ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ║ ║
cycy233-misllm-v9-0-1-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v9-0-1-v11-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-v9-0-1-v11-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v9-0-1-v11-mkmlizer: Downloaded to shared memory in 16.586s
cycy233-misllm-v9-0-1-v11-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v9-0-1-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v9-0-1-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 99.04it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 109.25it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 86.63it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v9-0-1-v11-mkmlizer: quantized model in 14.835s
cycy233-misllm-v9-0-1-v11-mkmlizer: Processed model cycy233/misllm_v9.0.1 in 33.692s
cycy233-misllm-v9-0-1-v11-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v9-0-1-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v9-0-1-v11/flywheel_model.0.safetensors
cycy233-misllm-v9-0-1-v11-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v9-0-1-v11-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-v9-0-1-v11-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-1-v11-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-v9-0-1-v11-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-1-v11-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-v9-0-1-v11-mkmlizer: warnings.warn(
cycy233-misllm-v9-0-1-v11-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-v9-0-1-v11-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v9-0-1-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v9-0-1-v11-mkmlizer: Saving duration: 0.390s
cycy233-misllm-v9-0-1-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.532s
cycy233-misllm-v9-0-1-v11-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v9-0-1-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v9-0-1-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v9-0-1-v11_reward
Failed to get response for submission cycy233-misllm-v9-0-3_v2: ('http://cycy233-misllm-v9-0-3-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '')
Job cycy233-misllm-v9-0-1-v11-mkmlizer completed after 62.76s with status: succeeded
Stopping job with name cycy233-misllm-v9-0-1-v11-mkmlizer
Pipeline stage MKMLizer completed in 66.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v9-0-1-v11
Waiting for inference service cycy233-misllm-v9-0-1-v11 to be ready
Inference service cycy233-misllm-v9-0-1-v11 ready after 40.38055920600891s
Pipeline stage ISVCDeployer completed in 47.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.977140188217163s
Received healthy response to inference request in 0.9756958484649658s
Received healthy response to inference request in 0.892413854598999s
Received healthy response to inference request in 0.943730354309082s
Received healthy response to inference request in 0.9168798923492432s
5 requests
0 failed requests
5th percentile: 0.8973070621490479
10th percentile: 0.9022002696990967
20th percentile: 0.9119866847991943
30th percentile: 0.9222499847412109
40th percentile: 0.9329901695251465
50th percentile: 0.943730354309082
60th percentile: 0.9565165519714356
70th percentile: 0.969302749633789
80th percentile: 1.1759847164154054
90th percentile: 1.5765624523162842
95th percentile: 1.7768513202667235
99th percentile: 1.937082414627075
mean time: 1.1411720275878907
Pipeline stage StressChecker completed in 6.26s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-misllm-v9-0-1_v11 status is now deployed due to DeploymentManager action
cycy233-misllm-v9-0-1_v11 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics