submission_id: cycy233-misllm-v6-0-5_v6
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.0.5
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': "### Instruction\nYou are a creative agent roleplaying as a character called {bot_name}. Stay true to the persona given, reply with long and descriptive sentences. Do not be repetitive. This is {bot_name}'s persona:\n{memory}", 'prompt_template': "### Input:\n # {bot_name}'s example conversation: \n{prompt}\n### Response: \n# Based on {bot_name}'s persona and the example conversation, please complete the following actual conversation as the Assistant (as {bot_name}) :\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: 2024-05-27T11:13:18+00:00
model_name: inference_test
model_eval_status: success
model_group: cycy233/misllm_v6.0.5
num_battles: 10495
num_wins: 5629
celo_rating: 1194.42
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: inference_test
ineligible_reason: propriety_total_count < 5000
language_model: cycy233/misllm_v6.0.5
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-27
win_ratio: 0.5363506431634112
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-0-5-v6-mkmlizer
Waiting for job on cycy233-misllm-v6-0-5-v6-mkmlizer to finish
cycy233-misllm-v6-0-5-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-0-5-v6-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-v6-0-5-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-0-5-v6-mkmlizer: Downloaded to shared memory in 15.862s
cycy233-misllm-v6-0-5-v6-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-0-5-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-0-5-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 94.50it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 105.10it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 84.04it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-0-5-v6-mkmlizer: quantized model in 14.760s
cycy233-misllm-v6-0-5-v6-mkmlizer: Processed model cycy233/misllm_v6.0.5 in 32.982s
cycy233-misllm-v6-0-5-v6-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-0-5-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-0-5-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6/tokenizer.model
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6/special_tokens_map.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6/config.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6/tokenizer_config.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6/tokenizer.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v6/flywheel_model.0.safetensors
cycy233-misllm-v6-0-5-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-0-5-v6-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-v6-0-5-v6-mkmlizer: warnings.warn(
cycy233-misllm-v6-0-5-v6-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-v6-0-5-v6-mkmlizer: warnings.warn(
cycy233-misllm-v6-0-5-v6-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-v6-0-5-v6-mkmlizer: warnings.warn(
cycy233-misllm-v6-0-5-v6-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-v6-0-5-v6-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-0-5-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-0-5-v6-mkmlizer: Saving duration: 0.407s
cycy233-misllm-v6-0-5-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.472s
cycy233-misllm-v6-0-5-v6-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-0-5-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-0-5-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/config.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/special_tokens_map.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/tokenizer_config.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/vocab.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/merges.txt
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/tokenizer.json
cycy233-misllm-v6-0-5-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v6_reward/reward.tensors
Job cycy233-misllm-v6-0-5-v6-mkmlizer completed after 62.9s with status: succeeded
Stopping job with name cycy233-misllm-v6-0-5-v6-mkmlizer
Pipeline stage MKMLizer completed in 67.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-0-5-v6
Waiting for inference service cycy233-misllm-v6-0-5-v6 to be ready
Inference service cycy233-misllm-v6-0-5-v6 ready after 40.197991371154785s
Pipeline stage ISVCDeployer completed in 48.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1858394145965576s
Received healthy response to inference request in 1.1806573867797852s
Received healthy response to inference request in 1.2052569389343262s
Received healthy response to inference request in 1.198861837387085s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2356219291687012s
Received healthy response to inference request in 1.192842721939087s
Received healthy response to inference request in 1.1984214782714844s
Received healthy response to inference request in 1.2304027080535889s
Received healthy response to inference request in 1.2133140563964844s
5 requests
0 failed requests
5th percentile: 1.1939584732055664
10th percentile: 1.1950742244720458
20th percentile: 1.197305727005005
30th percentile: 1.2013999938964843
40th percentile: 1.2073570251464845
50th percentile: 1.2133140563964844
60th percentile: 1.2201495170593262
70th percentile: 1.226984977722168
80th percentile: 1.2314465522766114
90th percentile: 1.2335342407226562
95th percentile: 1.2345780849456787
99th percentile: 1.2354131603240968
mean time: 1.214120578765869
Pipeline stage StressChecker completed in 32.96s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cycy233-misllm-v6-0-5_v6 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v6-0-5_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics