cycy233-misllm-v6-9-6-5

developer_uid: shiroe40

submission_id: cycy233-misllm-v6-9-6-5_v1

model_name: cycy233-misllm-v6-9-6-5_v1

model_group: cycy233/misllm_v6.9.6.5

status: rejected

timestamp: 2024-06-14T06:35:04+00:00

num_battles: 1230

num_wins: 635

celo_rating: 1197.37

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/misllm_v6.9.6.5

model_architecture: MistralForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 7241732096.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: cycy233-misllm-v6-9-6-5_v1

ineligible_reason: model is not deployable

is_internal_developer: False

language_model: cycy233/misllm_v6.9.6.5

model_size: 7B

ranking_group: single

us_pacific_date: 2024-06-13

win_ratio: 0.516260162601626

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}

model_eval_status: error

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-9-6-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v6-9-6-5-v1-mkmlizer to finish
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-6-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-9-6-5-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-v6-9-6-5-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Downloaded to shared memory in 25.205s
cycy233-misllm-v6-9-6-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-6-5-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:01, 97.20it/s]
Loading 0:  67%|██████▋   | 195/291 [00:01<00:00, 203.10it/s]
Loading 0:  87%|████████▋ | 252/291 [00:02<00:00, 116.23it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 68.27it/s] 
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-9-6-5-v1-mkmlizer: quantized model in 14.929s
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Processed model cycy233/misllm_v6.9.6.5 in 42.401s
cycy233-misllm-v6-9-6-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-6-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1/tokenizer.model
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1/config.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1/tokenizer_config.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1/special_tokens_map.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1/tokenizer.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-6-5-v1/flywheel_model.0.safetensors
cycy233-misllm-v6-9-6-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-6-5-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-v6-9-6-5-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-6-5-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-v6-9-6-5-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-6-5-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-v6-9-6-5-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-6-5-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-v6-9-6-5-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Saving duration: 0.408s
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.027s
cycy233-misllm-v6-9-6-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-9-6-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-9-6-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/config.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/tokenizer_config.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/special_tokens_map.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/vocab.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/merges.txt
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/tokenizer.json
cycy233-misllm-v6-9-6-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-9-6-5-v1_reward/reward.tensors
Job cycy233-misllm-v6-9-6-5-v1-mkmlizer completed after 63.04s with status: succeeded
Stopping job with name cycy233-misllm-v6-9-6-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 67.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-9-6-5-v1
Waiting for inference service cycy233-misllm-v6-9-6-5-v1 to be ready
Inference service cycy233-misllm-v6-9-6-5-v1 ready after 30.1732759475708s
Pipeline stage ISVCDeployer completed in 37.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0624992847442627s
Received healthy response to inference request in 2.0742461681365967s
Received healthy response to inference request in 13.173810243606567s
Received healthy response to inference request in 1.1905193328857422s
Received healthy response to inference request in 1.1503498554229736s
5 requests
0 failed requests
5th percentile: 1.1583837509155273
10th percentile: 1.166417646408081
20th percentile: 1.1824854373931886
30th percentile: 1.3649153232574462
40th percentile: 1.7137073040008546
50th percentile: 2.0624992847442627
60th percentile: 2.0671980381011963
70th percentile: 2.07189679145813
80th percentile: 4.294158983230593
90th percentile: 8.733984613418581
95th percentile: 10.95389742851257
99th percentile: 12.729827680587768
mean time: 3.9302849769592285
Pipeline stage StressChecker completed in 20.26s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-v6-9-6-5_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-9-6-5_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.