submission_id: cycy233-misllm-v4-5_v4
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': "### 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': 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: 2024-05-22T08:23:12+00:00
model_name: inference_test
model_eval_status: success
model_group: cycy233/misllm_v4.5
num_battles: 9986
num_wins: 5226
celo_rating: 1187.0
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: inference_test
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: 2024-05-22
win_ratio: 0.5233326657320249
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v4-5-v4-mkmlizer
Waiting for job on cycy233-misllm-v4-5-v4-mkmlizer to finish
cycy233-misllm-v4-5-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v4-5-v4-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ /___/ ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ belonging to: ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v4-5-v4-mkmlizer: ║ ║
cycy233-misllm-v4-5-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v4-5-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v4-5-v4-mkmlizer: Downloaded to shared memory in 20.515s
cycy233-misllm-v4-5-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v4-5-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v4-5-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 73.61it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 83.91it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 75.27it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v4-5-v4-mkmlizer: quantized model in 11.831s
cycy233-misllm-v4-5-v4-mkmlizer: Processed model cycy233/misllm_v4.5 in 33.323s
cycy233-misllm-v4-5-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v4-5-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v4-5-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4
cycy233-misllm-v4-5-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4/special_tokens_map.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4/config.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4/tokenizer_config.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4/tokenizer.model
cycy233-misllm-v4-5-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4/tokenizer.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v4-5-v4/flywheel_model.0.safetensors
cycy233-misllm-v4-5-v4-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-v4-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-v4-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-v4-mkmlizer: warnings.warn(
cycy233-misllm-v4-5-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v4-5-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v4-5-v4-mkmlizer: Saving duration: 0.257s
cycy233-misllm-v4-5-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.045s
cycy233-misllm-v4-5-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v4-5-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v4-5-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/config.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/tokenizer_config.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/special_tokens_map.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/merges.txt
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/vocab.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/tokenizer.json
cycy233-misllm-v4-5-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v4-5-v4_reward/reward.tensors
Job cycy233-misllm-v4-5-v4-mkmlizer completed after 52.87s with status: succeeded
Stopping job with name cycy233-misllm-v4-5-v4-mkmlizer
Pipeline stage MKMLizer completed in 56.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v4-5-v4
Waiting for inference service cycy233-misllm-v4-5-v4 to be ready
Inference service cycy233-misllm-v4-5-v4 ready after 40.22555494308472s
Pipeline stage ISVCDeployer completed in 47.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.16614031791687s
Received healthy response to inference request in 1.150892734527588s
Received healthy response to inference request in 1.1771187782287598s
Received healthy response to inference request in 1.1618211269378662s
Received healthy response to inference request in 1.1735484600067139s
5 requests
0 failed requests
5th percentile: 1.1530784130096436
10th percentile: 1.1552640914916992
20th percentile: 1.1596354484558105
30th percentile: 1.1641665935516357
40th percentile: 1.1688575267791748
50th percentile: 1.1735484600067139
60th percentile: 1.1749765872955322
70th percentile: 1.1764047145843506
80th percentile: 1.374923086166382
90th percentile: 1.770531702041626
95th percentile: 1.968336009979248
99th percentile: 2.126579456329346
mean time: 1.3659042835235595
Pipeline stage StressChecker completed in 7.43s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v4-5_v4 status is now deployed due to DeploymentManager action
cycy233-misllm-v4-5_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics