developer_uid: shiroe40
submission_id: cycy233-misllm-v5-3_v4
model_name: inference_test
model_group: cycy233/misllm_v5.3
status: torndown
timestamp: 2024-05-23T04:27:12+00:00
num_battles: 13639
num_wins: 7145
celo_rating: 1186.45
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v5.3
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: inference_test
is_internal_developer: False
language_model: cycy233/misllm_v5.3
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-22
win_ratio: 0.5238653860253685
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: {'bot_template': '### {bot_name}: {message}\n', '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", 'response_template': '### {bot_name}:', 'truncate_by_message': True, 'user_template': '### {user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v5-3-v4-mkmlizer
Waiting for job on cycy233-misllm-v5-3-v4-mkmlizer to finish
cycy233-misllm-v5-3-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v5-3-v4-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v5-3-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v5-3-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v5-3-v4-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v5-3-v4-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v5-3-v4-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v5-3-v4-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v5-3-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v5-3-v4-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-3-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v5-3-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-v5-3-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v5-3-v4-mkmlizer: Downloaded to shared memory in 20.179s
cycy233-misllm-v5-3-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-3-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-3-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 87.46it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 101.81it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 83.59it/s] 
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-3-v4-mkmlizer: quantized model in 15.553s
cycy233-misllm-v5-3-v4-mkmlizer: Processed model cycy233/misllm_v5.3 in 38.079s
cycy233-misllm-v5-3-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-3-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-3-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4
cycy233-misllm-v5-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4/tokenizer_config.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4/special_tokens_map.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4/tokenizer.model
cycy233-misllm-v5-3-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4/config.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4/tokenizer.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-3-v4/flywheel_model.0.safetensors
cycy233-misllm-v5-3-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v5-3-v4-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-v5-3-v4-mkmlizer:   warnings.warn(
cycy233-misllm-v5-3-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-v5-3-v4-mkmlizer:   warnings.warn(
cycy233-misllm-v5-3-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-v5-3-v4-mkmlizer:   warnings.warn(
cycy233-misllm-v5-3-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-v5-3-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-3-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-3-v4-mkmlizer: Saving duration: 0.389s
cycy233-misllm-v5-3-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.516s
cycy233-misllm-v5-3-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-3-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-3-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/config.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/special_tokens_map.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/tokenizer_config.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/merges.txt
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/vocab.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/tokenizer.json
cycy233-misllm-v5-3-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-3-v4_reward/reward.tensors
Job cycy233-misllm-v5-3-v4-mkmlizer completed after 62.72s with status: succeeded
Stopping job with name cycy233-misllm-v5-3-v4-mkmlizer
Pipeline stage MKMLizer completed in 66.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-3-v4
Waiting for inference service cycy233-misllm-v5-3-v4 to be ready
Inference service cycy233-misllm-v5-3-v4 ready after 30.16604256629944s
Pipeline stage ISVCDeployer completed in 37.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8610336780548096s
Received healthy response to inference request in 1.1711757183074951s
Received healthy response to inference request in 1.0870447158813477s
Received healthy response to inference request in 1.118253469467163s
Received healthy response to inference request in 1.1731832027435303s
5 requests
0 failed requests
5th percentile: 1.0932864665985107
10th percentile: 1.0995282173156737
20th percentile: 1.11201171875
30th percentile: 1.1288379192352296
40th percentile: 1.1500068187713623
50th percentile: 1.1711757183074951
60th percentile: 1.1719787120819092
70th percentile: 1.1727817058563232
80th percentile: 1.3107532978057863
90th percentile: 1.585893487930298
95th percentile: 1.7234635829925535
99th percentile: 1.8335196590423584
mean time: 1.2821381568908692
Pipeline stage StressChecker completed in 6.98s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v5-3_v4 status is now deployed due to DeploymentManager action
cycy233-misllm-v5-3_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-3_v4
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-3-v4 is running
Tearing down inference service cycy233-misllm-v5-3-v4
Toredown service cycy233-misllm-v5-3-v4
Pipeline stage ISVCDeleter completed in 5.52s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-3-v4/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-3-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-3-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-3-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-3-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-3-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-3-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-3-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-3-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-3-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-3-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-3-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-3-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.43s
cycy233-misllm-v5-3_v4 status is now torndown due to DeploymentManager action