developer_uid: shiroe40
submission_id: cycy233-misllm-v7-0-3_v1
model_name: base
model_group: cycy233/misllm_v7.0.3
status: torndown
timestamp: 2024-06-08T12:44:53+00:00
num_battles: 6458
num_wins: 3362
celo_rating: 1194.72
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v7.0.3
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
is_internal_developer: False
language_model: cycy233/misllm_v7.0.3
model_size: 7B
ranking_group: single
us_pacific_date: 2024-06-08
win_ratio: 0.5205946113347786
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': True}
model_eval_status: success
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': True, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v7-0-3-v1-mkmlizer
Waiting for job on cycy233-misllm-v7-0-3-v1-mkmlizer to finish
cycy233-misllm-v7-0-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v7-0-3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-0-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v7-0-3-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-v7-0-3-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v7-0-3-v1-mkmlizer: Downloaded to shared memory in 29.781s
cycy233-misllm-v7-0-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v7-0-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v7-0-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 79.07it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 89.86it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 71.55it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v7-0-3-v1-mkmlizer: Processed model cycy233/misllm_v7.0.3 in 49.784s
cycy233-misllm-v7-0-3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v7-0-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v7-0-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1/config.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1/special_tokens_map.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1/tokenizer_config.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1/tokenizer.model
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1/tokenizer.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v7-0-3-v1/flywheel_model.0.safetensors
cycy233-misllm-v7-0-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v7-0-3-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-v7-0-3-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v7-0-3-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-v7-0-3-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v7-0-3-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-v7-0-3-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v7-0-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v7-0-3-v1-mkmlizer: Saving duration: 0.468s
cycy233-misllm-v7-0-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.392s
cycy233-misllm-v7-0-3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v7-0-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v7-0-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/config.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/special_tokens_map.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/tokenizer_config.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/merges.txt
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/vocab.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/tokenizer.json
cycy233-misllm-v7-0-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v7-0-3-v1_reward/reward.tensors
Job cycy233-misllm-v7-0-3-v1-mkmlizer completed after 73.19s with status: succeeded
Stopping job with name cycy233-misllm-v7-0-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v7-0-3-v1
Waiting for inference service cycy233-misllm-v7-0-3-v1 to be ready
Inference service cycy233-misllm-v7-0-3-v1 ready after 40.39420795440674s
Pipeline stage ISVCDeployer completed in 47.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0195229053497314s
Received healthy response to inference request in 0.8463156223297119s
Received healthy response to inference request in 1.2341740131378174s
Received healthy response to inference request in 0.9098854064941406s
Received healthy response to inference request in 1.216881513595581s
5 requests
0 failed requests
5th percentile: 0.8590295791625977
10th percentile: 0.8717435359954834
20th percentile: 0.8971714496612548
30th percentile: 0.9712846279144287
40th percentile: 1.0940830707550049
50th percentile: 1.216881513595581
60th percentile: 1.2237985134124756
70th percentile: 1.2307155132293701
80th percentile: 1.3912437915802003
90th percentile: 1.7053833484649659
95th percentile: 1.8624531269073485
99th percentile: 1.988108949661255
mean time: 1.2453558921813965
Pipeline stage StressChecker completed in 7.00s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v7-0-3_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v7-0-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v7-0-3_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v7-0-3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v7-0-3-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-0-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-0-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-0-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-0-3-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-0-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v7-0-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-0-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-0-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-0-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-0-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-0-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-0-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.57s
cycy233-misllm-v7-0-3_v1 status is now torndown due to DeploymentManager action