cycy233-misllm-v5-4

developer_uid: shiroe40

submission_id: cycy233-misllm-v5-4_v2

model_name: inference_test

model_group: cycy233/misllm_v5.4

status: torndown

timestamp: 2024-05-23T08:24:14+00:00

num_battles: 17030

num_wins: 8848

celo_rating: 1186.14

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/misllm_v5.4

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_v5.4

model_size: 7B

ranking_group: single

us_pacific_date: 2024-05-23

win_ratio: 0.519553728714034

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\u2028', 'user_template': '### {user_name}: {message}\n', 'response_template': '### {bot_name}:', 'truncate_by_message': True}

reward_formatter: {'bot_template': '### {bot_name}: {message}\n\u2028', '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-v5-4-v2-mkmlizer
Waiting for job on cycy233-misllm-v5-4-v2-mkmlizer to finish
cycy233-misllm-v5-4-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v5-4-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v5-4-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v5-4-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v5-4-v2-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v5-4-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v5-4-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v5-4-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v5-4-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v5-4-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v5-4-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v5-4-v2-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-v5-4-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v5-4-v2-mkmlizer: Downloaded to shared memory in 14.543s
cycy233-misllm-v5-4-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v5-4-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v5-4-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:01, 97.40it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 98.47it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 82.09it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v5-4-v2-mkmlizer: quantized model in 14.516s
cycy233-misllm-v5-4-v2-mkmlizer: Processed model cycy233/misllm_v5.4 in 31.308s
cycy233-misllm-v5-4-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v5-4-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v5-4-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2
cycy233-misllm-v5-4-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2/config.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2/special_tokens_map.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2/tokenizer.model
cycy233-misllm-v5-4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2/tokenizer.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2/tokenizer_config.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v5-4-v2/flywheel_model.0.safetensors
cycy233-misllm-v5-4-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v5-4-v2-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-v5-4-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v5-4-v2-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-v5-4-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v5-4-v2-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-v5-4-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v5-4-v2-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-v5-4-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v5-4-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v5-4-v2-mkmlizer: Saving duration: 0.400s
cycy233-misllm-v5-4-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.838s
cycy233-misllm-v5-4-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v5-4-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v5-4-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/special_tokens_map.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/config.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/tokenizer_config.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/merges.txt
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/vocab.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/tokenizer.json
cycy233-misllm-v5-4-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v5-4-v2_reward/reward.tensors
Job cycy233-misllm-v5-4-v2-mkmlizer completed after 62.52s with status: succeeded
Stopping job with name cycy233-misllm-v5-4-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v5-4-v2
Waiting for inference service cycy233-misllm-v5-4-v2 to be ready
Inference service cycy233-misllm-v5-4-v2 ready after 30.161654710769653s
Pipeline stage ISVCDeployer completed in 38.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8010518550872803s
Received healthy response to inference request in 1.066439151763916s
Received healthy response to inference request in 1.0278048515319824s
Received healthy response to inference request in 1.1627726554870605s
Received healthy response to inference request in 1.0695419311523438s
5 requests
0 failed requests
5th percentile: 1.035531711578369
10th percentile: 1.0432585716247558
20th percentile: 1.0587122917175293
30th percentile: 1.0670597076416015
40th percentile: 1.0683008193969727
50th percentile: 1.0695419311523438
60th percentile: 1.1068342208862305
70th percentile: 1.1441265106201173
80th percentile: 1.2904284954071046
90th percentile: 1.5457401752471924
95th percentile: 1.6733960151672362
99th percentile: 1.7755206871032714
mean time: 1.2255220890045166
Pipeline stage StressChecker completed in 6.77s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
cycy233-misllm-v5-4_v2 status is now deployed due to DeploymentManager action
cycy233-misllm-v5-4_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v5-4_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v5-4-v2 is running
Tearing down inference service cycy233-misllm-v5-4-v2
Toredown service cycy233-misllm-v5-4-v2
Pipeline stage ISVCDeleter completed in 4.66s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-4-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v5-4-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v5-4-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v5-4-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.47s
cycy233-misllm-v5-4_v2 status is now torndown due to DeploymentManager action