cycy233-misllm-v5-2

developer_uid: shiroe40

submission_id: cycy233-misllm-v5-2_v1

model_name: inference_test

model_group: cycy233/misllm_v5.2

status: torndown

timestamp: 2024-05-23T02:08:15+00:00

num_battles: 15463

num_wins: 7817

celo_rating: 1178.83

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/misllm_v5.2

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_v5.2

model_size: 7B

ranking_group: single

us_pacific_date: 2024-05-22

win_ratio: 0.5055293280734657

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\u2028", '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': "### 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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v5-2-v1-mkmlizer
Waiting for job on cycy233-misllm-v5-2-v1-mkmlizer to finish
cycy233-misllm-v5-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v5-2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v5-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v5-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v5-2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v5-2-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v5-2-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v5-2-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v5-2-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v5-2-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v5-2-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-v5-2-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v5-2-v1-mkmlizer: Downloaded to shared memory in 52.689s
cycy233-misllm-v5-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 70.79it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:01, 80.52it/s]
Loading 0: 100%|██████████| 291/291 [00:04<00:00, 70.67it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-2-v1-mkmlizer: quantized model in 15.813s
cycy233-misllm-v5-2-v1-mkmlizer: Processed model cycy233/misllm_v5.2 in 70.765s
cycy233-misllm-v5-2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1
cycy233-misllm-v5-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1/special_tokens_map.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1/tokenizer_config.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1/config.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1/tokenizer.model
cycy233-misllm-v5-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1/tokenizer.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-2-v1/flywheel_model.0.safetensors
cycy233-misllm-v5-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v5-2-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-v5-2-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v5-2-v1-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-v5-2-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v5-2-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-v5-2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-2-v1-mkmlizer: Saving duration: 0.452s
cycy233-misllm-v5-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 23.067s
cycy233-misllm-v5-2-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/special_tokens_map.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/merges.txt
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/config.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/tokenizer_config.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/vocab.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/tokenizer.json
cycy233-misllm-v5-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-2-v1_reward/reward.tensors
Job cycy233-misllm-v5-2-v1-mkmlizer completed after 144.01s with status: succeeded
Stopping job with name cycy233-misllm-v5-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-2-v1
Waiting for inference service cycy233-misllm-v5-2-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service cycy233-misllm-v5-2-v1 ready after 30.211586713790894s
Pipeline stage ISVCDeployer completed in 37.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0495567321777344s
Received healthy response to inference request in 1.195328950881958s
Received healthy response to inference request in 1.269028663635254s
Received healthy response to inference request in 1.0586960315704346s
Received healthy response to inference request in 1.186647891998291s
5 requests
0 failed requests
5th percentile: 1.0842864036560058
10th percentile: 1.109876775741577
20th percentile: 1.1610575199127198
30th percentile: 1.1883841037750245
40th percentile: 1.1918565273284911
50th percentile: 1.195328950881958
60th percentile: 1.2248088359832763
70th percentile: 1.2542887210845948
80th percentile: 1.42513427734375
90th percentile: 1.7373455047607422
95th percentile: 1.8934511184692382
99th percentile: 2.018335609436035
mean time: 1.3518516540527343
Pipeline stage StressChecker completed in 7.33s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cycy233-misllm-v5-2_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v5-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-2_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-2-v1 is running
Tearing down inference service cycy233-misllm-v5-2-v1
Toredown service cycy233-misllm-v5-2-v1
Pipeline stage ISVCDeleter completed in 5.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-2-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-2-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.19s
cycy233-misllm-v5-2_v1 status is now torndown due to DeploymentManager action