developer_uid: shiroe40
submission_id: cycy233-misllm-v6-2-2-5_v10
model_name: inference_test
model_group: cycy233/misllm_v6.2.2.5
status: torndown
timestamp: 2024-05-31T06:22:25+00:00
num_battles: 12139
num_wins: 6051
celo_rating: 1185.53
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v6.2.2.5
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: inference_test
is_internal_developer: False
language_model: cycy233/misllm_v6.2.2.5
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-30
win_ratio: 0.49847598648982616
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': False}
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': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-2-2-5-v10-mkmlizer
Waiting for job on cycy233-misllm-v6-2-2-5-v10-mkmlizer to finish
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ║ ║
cycy233-misllm-v6-2-2-5-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-2-2-5-v10-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-v6-2-2-5-v10-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Downloaded to shared memory in 16.493s
cycy233-misllm-v6-2-2-5-v10-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 95.29it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 107.69it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 84.82it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-2-2-5-v10-mkmlizer: quantized model in 14.723s
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Processed model cycy233/misllm_v6.2.2.5 in 33.473s
cycy233-misllm-v6-2-2-5-v10-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-2-2-5-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v10
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v10/config.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v10/special_tokens_map.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v10/tokenizer.model
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v10/tokenizer_config.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v10/tokenizer.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-2-2-5-v10-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-v6-2-2-5-v10-mkmlizer: warnings.warn(
cycy233-misllm-v6-2-2-5-v10-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-v6-2-2-5-v10-mkmlizer: warnings.warn(
cycy233-misllm-v6-2-2-5-v10-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-v6-2-2-5-v10-mkmlizer: warnings.warn(
cycy233-misllm-v6-2-2-5-v10-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-v6-2-2-5-v10-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Saving duration: 0.396s
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.886s
cycy233-misllm-v6-2-2-5-v10-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-2-2-5-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-2-2-5-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/config.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/special_tokens_map.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/vocab.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/merges.txt
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/tokenizer_config.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/tokenizer.json
cycy233-misllm-v6-2-2-5-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-2-2-5-v10_reward/reward.tensors
Job cycy233-misllm-v6-2-2-5-v10-mkmlizer completed after 52.54s with status: succeeded
Stopping job with name cycy233-misllm-v6-2-2-5-v10-mkmlizer
Pipeline stage MKMLizer completed in 53.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-2-2-5-v10
Waiting for inference service cycy233-misllm-v6-2-2-5-v10 to be ready
Inference service cycy233-misllm-v6-2-2-5-v10 ready after 40.218103647232056s
Pipeline stage ISVCDeployer completed in 46.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.10605525970459s
Received healthy response to inference request in 1.1878371238708496s
Received healthy response to inference request in 1.1848900318145752s
Received healthy response to inference request in 1.1024370193481445s
Received healthy response to inference request in 1.1878552436828613s
5 requests
0 failed requests
5th percentile: 1.1189276218414306
10th percentile: 1.1354182243347168
20th percentile: 1.1683994293212892
30th percentile: 1.1854794502258301
40th percentile: 1.1866582870483398
50th percentile: 1.1878371238708496
60th percentile: 1.1878443717956544
70th percentile: 1.187851619720459
80th percentile: 1.3714952468872073
90th percentile: 1.7387752532958984
95th percentile: 1.922415256500244
99th percentile: 2.0693272590637206
mean time: 1.3538149356842042
Pipeline stage StressChecker completed in 7.37s
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-v6-2-2-5_v10 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-2-2-5_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v6-2-2-5_v10
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v6-2-2-5-v10 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-2-2-5-v10/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-2-2-5-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-2-2-5-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-2-2-5-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-2-2-5-v10/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v6-2-2-5-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v6-2-2-5-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.62s
cycy233-misllm-v6-2-2-5_v10 status is now torndown due to DeploymentManager action