developer_uid: shiroe40
submission_id: cycy233-misllm-v7-9-3_v1
model_name: base
model_group: cycy233/misllm_v7.9.3
status: torndown
timestamp: 2024-06-18T02:37:35+00:00
num_battles: 12904
num_wins: 6600
celo_rating: 1194.82
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v7.9.3
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_v7.9.3
model_size: 7B
ranking_group: single
us_pacific_date: 2024-06-17
win_ratio: 0.5114693118412895
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}
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-v7-9-3-v1-mkmlizer
Waiting for job on cycy233-misllm-v7-9-3-v1-mkmlizer to finish
cycy233-misllm-v7-9-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v7-9-3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ║                                                                     ║
cycy233-misllm-v7-9-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v7-9-3-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-v7-9-3-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v7-9-3-v1-mkmlizer: Downloaded to shared memory in 27.782s
cycy233-misllm-v7-9-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v7-9-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v7-9-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:00, 569.96it/s]
Loading 0:  39%|███▉      | 114/291 [00:01<00:02, 85.23it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 91.07it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 75.64it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v7-9-3-v1-mkmlizer: quantized model in 15.043s
cycy233-misllm-v7-9-3-v1-mkmlizer: Processed model cycy233/misllm_v7.9.3 in 45.061s
cycy233-misllm-v7-9-3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v7-9-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v7-9-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v7-9-3-v1
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v7-9-3-v1/config.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v7-9-3-v1/special_tokens_map.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v7-9-3-v1/tokenizer_config.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v7-9-3-v1/tokenizer.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v7-9-3-v1/tokenizer.model
cycy233-misllm-v7-9-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v7-9-3-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-v7-9-3-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v7-9-3-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-v7-9-3-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v7-9-3-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-v7-9-3-v1-mkmlizer:   warnings.warn(
cycy233-misllm-v7-9-3-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-v7-9-3-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v7-9-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v7-9-3-v1-mkmlizer: Saving duration: 0.385s
cycy233-misllm-v7-9-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.063s
cycy233-misllm-v7-9-3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v7-9-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v7-9-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward/config.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward/special_tokens_map.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward/merges.txt
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward/vocab.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward/tokenizer_config.json
cycy233-misllm-v7-9-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v7-9-3-v1_reward/tokenizer.json
Job cycy233-misllm-v7-9-3-v1-mkmlizer completed after 74.25s with status: succeeded
Stopping job with name cycy233-misllm-v7-9-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v7-9-3-v1
Waiting for inference service cycy233-misllm-v7-9-3-v1 to be ready
Inference service cycy233-misllm-v7-9-3-v1 ready after 40.30592679977417s
Pipeline stage ISVCDeployer completed in 47.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.901930570602417s
Received healthy response to inference request in 1.1705596446990967s
Received healthy response to inference request in 1.1753926277160645s
Received healthy response to inference request in 1.1557414531707764s
Received healthy response to inference request in 13.548362970352173s
5 requests
0 failed requests
5th percentile: 1.1587050914764405
10th percentile: 1.1616687297821044
20th percentile: 1.1675960063934325
30th percentile: 1.1715262413024903
40th percentile: 1.1734594345092773
50th percentile: 1.1753926277160645
60th percentile: 1.4660078048706053
70th percentile: 1.7566229820251464
80th percentile: 4.23121705055237
90th percentile: 8.889790010452272
95th percentile: 11.21907649040222
99th percentile: 13.082505674362181
mean time: 3.7903974533081053
Pipeline stage StressChecker completed in 19.57s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-misllm-v7-9-3_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v7-9-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-misllm-v7-9-3_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-misllm-v7-9-3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.31s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-misllm-v7-9-3-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-9-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-9-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-9-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-9-3-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key cycy233-misllm-v7-9-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-misllm-v7-9-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-9-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-9-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-9-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-9-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-9-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-misllm-v7-9-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.81s
cycy233-misllm-v7-9-3_v1 status is now torndown due to DeploymentManager action