submission_id: cycy233-misllm-v4-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v4.5
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, '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: 2024-05-21T06:43:44+00:00
model_name: base
model_eval_status: success
model_group: cycy233/misllm_v4.5
num_battles: 15897
num_wins: 8517
celo_rating: 1192.92
safety_score: 0.98
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: base
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: 2024-05-20
win_ratio: 0.5357614644272505
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v4-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v4-5-v1-mkmlizer to finish
cycy233-misllm-v4-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v4-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v4-5-v1-mkmlizer: ║ ║
cycy233-misllm-v4-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v4-5-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-v4-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v4-5-v1-mkmlizer: Downloaded to shared memory in 25.181s
cycy233-misllm-v4-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v4-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v4-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 89.94it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 99.14it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 84.13it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v4-5-v1-mkmlizer: quantized model in 10.946s
cycy233-misllm-v4-5-v1-mkmlizer: Processed model cycy233/misllm_v4.5 in 37.056s
cycy233-misllm-v4-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v4-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v4-5-v1/flywheel_model.0.safetensors
cycy233-misllm-v4-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v4-5-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-v4-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-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-v4-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-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-v4-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-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-v4-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v4-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v4-5-v1-mkmlizer: Saving duration: 0.255s
cycy233-misllm-v4-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.096s
cycy233-misllm-v4-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v4-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v4-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/special_tokens_map.json
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/config.json
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/merges.txt
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/vocab.json
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/tokenizer.json
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/tokenizer_config.json
cycy233-misllm-v4-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v4-5-v1_reward/reward.tensors
Job cycy233-misllm-v4-5-v1-mkmlizer completed after 62.48s with status: succeeded
Stopping job with name cycy233-misllm-v4-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 65.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v4-5-v1
Waiting for inference service cycy233-misllm-v4-5-v1 to be ready
Inference service cycy233-misllm-v4-5-v1 ready after 40.186323165893555s
Pipeline stage ISVCDeployer completed in 47.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8021667003631592s
Received healthy response to inference request in 1.0637729167938232s
Received healthy response to inference request in 1.1915881633758545s
Received healthy response to inference request in 1.170856237411499s
Received healthy response to inference request in 1.1605887413024902s
5 requests
0 failed requests
5th percentile: 1.0831360816955566
10th percentile: 1.10249924659729
20th percentile: 1.1412255764007568
30th percentile: 1.162642240524292
40th percentile: 1.1667492389678955
50th percentile: 1.170856237411499
60th percentile: 1.1791490077972413
70th percentile: 1.1874417781829834
80th percentile: 1.3137038707733155
90th percentile: 1.5579352855682373
95th percentile: 1.6800509929656982
99th percentile: 1.777743558883667
mean time: 1.2777945518493652
Pipeline stage StressChecker completed in 7.18s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v4-5_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v4-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics