submission_id: cycy233-misllm-v7-7-3_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v7.7.3
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: 2024-06-17T03:03:35+00:00
model_name: base_f
model_eval_status: success
model_group: cycy233/misllm_v7.7.3
num_battles: 19918
num_wins: 10122
celo_rating: 1195.05
propriety_score: 0.6807059333044608
propriety_total_count: 9236.0
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_f
ineligible_reason: None
language_model: cycy233/misllm_v7.7.3
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-16
win_ratio: 0.5081835525655186
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v7-7-3-v2-mkmlizer
Waiting for job on cycy233-misllm-v7-7-3-v2-mkmlizer to finish
cycy233-misllm-v7-7-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ /___/ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ belonging to: ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ║ ║
cycy233-misllm-v7-7-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v7-7-3-v2-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-v7-7-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v7-7-3-v2-mkmlizer: Downloaded to shared memory in 19.347s
cycy233-misllm-v7-7-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v7-7-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v7-7-3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 88.37it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 103.22it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 84.68it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v7-7-3-v2-mkmlizer: quantized model in 15.449s
cycy233-misllm-v7-7-3-v2-mkmlizer: Processed model cycy233/misllm_v7.7.3 in 37.195s
cycy233-misllm-v7-7-3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v7-7-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v7-7-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2/special_tokens_map.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2/config.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2/tokenizer.model
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2/tokenizer.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2/tokenizer_config.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v7-7-3-v2/flywheel_model.0.safetensors
cycy233-misllm-v7-7-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v7-7-3-v2-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-v7-7-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v7-7-3-v2-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-v7-7-3-v2-mkmlizer: warnings.warn(
cycy233-misllm-v7-7-3-v2-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-v7-7-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v7-7-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v7-7-3-v2-mkmlizer: Saving duration: 0.414s
cycy233-misllm-v7-7-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.317s
cycy233-misllm-v7-7-3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v7-7-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v7-7-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/config.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/tokenizer_config.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/special_tokens_map.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/vocab.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/merges.txt
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/tokenizer.json
cycy233-misllm-v7-7-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v7-7-3-v2_reward/reward.tensors
Job cycy233-misllm-v7-7-3-v2-mkmlizer completed after 72.76s with status: succeeded
Stopping job with name cycy233-misllm-v7-7-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v7-7-3-v2
Waiting for inference service cycy233-misllm-v7-7-3-v2 to be ready
Inference service cycy233-misllm-v7-7-3-v2 ready after 40.24884080886841s
Pipeline stage ISVCDeployer completed in 47.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1408212184906006s
Received healthy response to inference request in 1.5855419635772705s
Received healthy response to inference request in 1.263791561126709s
Received healthy response to inference request in 1.1905031204223633s
Received healthy response to inference request in 1.1860990524291992s
5 requests
0 failed requests
5th percentile: 1.1869798660278321
10th percentile: 1.1878606796264648
20th percentile: 1.1896223068237304
30th percentile: 1.2051608085632324
40th percentile: 1.2344761848449708
50th percentile: 1.263791561126709
60th percentile: 1.3924917221069335
70th percentile: 1.5211918830871582
80th percentile: 1.6965978145599365
90th percentile: 1.9187095165252686
95th percentile: 2.0297653675079346
99th percentile: 2.1186100482940673
mean time: 1.4733513832092284
Pipeline stage StressChecker completed in 7.96s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
cycy233-misllm-v7-7-3_v2 status is now deployed due to DeploymentManager action
cycy233-misllm-v7-7-3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics