submission_id: cycy233-misllm-v4-5_v3
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v4.5
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: 2024-05-21T08:50:36+00:00
model_name: role
model_eval_status: success
model_group: cycy233/misllm_v4.5
num_battles: 10316
num_wins: 5663
celo_rating: 1196.92
safety_score: 0.96
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: role
ineligible_reason: propriety_total_count < 5000
language_model: cycy233/misllm_v4.5
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-21
win_ratio: 0.5489530825901512
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v4-5-v3-mkmlizer
Waiting for job on cycy233-misllm-v4-5-v3-mkmlizer to finish
Stopping job with name cycy233-misllm-v4-5-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-misllm-v4-5-v3-mkmlizer
Waiting for job on cycy233-misllm-v4-5-v3-mkmlizer to finish
cycy233-misllm-v4-5-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v4-5-v3-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ /___/ ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ belonging to: ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v4-5-v3-mkmlizer: ║ ║
cycy233-misllm-v4-5-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v4-5-v3-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-v4-5-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v4-5-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:01, 104.53it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 115.76it/s] Loading 0: 100%|██████████| 291/291 [00:02<00:00, 93.37it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v4-5-v3-mkmlizer: quantized model in 10.656s
cycy233-misllm-v4-5-v3-mkmlizer: Processed model cycy233/misllm_v4.5 in 27.646s
cycy233-misllm-v4-5-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v4-5-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v4-5-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3
cycy233-misllm-v4-5-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3/config.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3/special_tokens_map.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3/tokenizer_config.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3/tokenizer.model
cycy233-misllm-v4-5-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3/tokenizer.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v4-5-v3/flywheel_model.0.safetensors
cycy233-misllm-v4-5-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v4-5-v3-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-v4-5-v3-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-v3-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-v4-5-v3-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-v3-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-v4-5-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v4-5-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v4-5-v3-mkmlizer: Saving duration: 0.255s
cycy233-misllm-v4-5-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.878s
cycy233-misllm-v4-5-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v4-5-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v4-5-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/config.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/special_tokens_map.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/tokenizer_config.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/merges.txt
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/vocab.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/tokenizer.json
cycy233-misllm-v4-5-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v4-5-v3_reward/reward.tensors
Job cycy233-misllm-v4-5-v3-mkmlizer completed after 53.42s with status: succeeded
Stopping job with name cycy233-misllm-v4-5-v3-mkmlizer
Pipeline stage MKMLizer completed in 57.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v4-5-v3
Waiting for inference service cycy233-misllm-v4-5-v3 to be ready
Inference service cycy233-misllm-v4-5-v3 ready after 30.191733598709106s
Pipeline stage ISVCDeployer completed in 37.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9539475440979004s
Received healthy response to inference request in 1.1942405700683594s
Received healthy response to inference request in 1.180558681488037s
Received healthy response to inference request in 1.189582109451294s
Received healthy response to inference request in 1.1668221950531006s
5 requests
0 failed requests
5th percentile: 1.169569492340088
10th percentile: 1.1723167896270752
20th percentile: 1.1778113842010498
30th percentile: 1.1823633670806886
40th percentile: 1.1859727382659913
50th percentile: 1.189582109451294
60th percentile: 1.19144549369812
70th percentile: 1.1933088779449463
80th percentile: 1.3461819648742677
90th percentile: 1.650064754486084
95th percentile: 1.802006149291992
99th percentile: 1.9235592651367188
mean time: 1.3370302200317383
Pipeline stage StressChecker completed in 7.36s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v4-5_v3 status is now deployed due to DeploymentManager action
cycy233-misllm-v4-5_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics