developer_uid: Hastagaras
submission_id: hastagaras-lm3-8b-calmtu_5756_v2
model_name: calmtune-debugging
model_group: Hastagaras/lm3-8b-calmtu
status: torndown
timestamp: 2024-05-11T23:39:11+00:00
num_battles: 27785
num_wins: 14661
celo_rating: 1186.32
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/lm3-8b-calmtune-broken
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: calmtune-debugging
is_internal_developer: False
language_model: Hastagaras/lm3-8b-calmtune-broken
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-11
win_ratio: 0.5276588087097355
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 35, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': 'Notes: {prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer
Waiting for job on hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer to finish
Stopping job with name hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer
Waiting for job on hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer to finish
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Downloaded to shared memory in 12.396s
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  35%|███▌      | 103/291 [00:01<00:01, 101.89it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 104.95it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 27.24it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: quantized model in 21.192s
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Processed model Hastagaras/lm3-8b-calmtune-broken in 35.266s
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v2/flywheel_model.0.safetensors
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-calmtu-5756-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()
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Saving duration: 0.255s
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.826s
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/special_tokens_map.json
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/config.json
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/tokenizer_config.json
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/merges.txt
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/vocab.json
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/tokenizer.json
hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v2_reward/reward.tensors
Job hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer completed after 65.26s with status: succeeded
Stopping job with name hastagaras-lm3-8b-calmtu-5756-v2-mkmlizer
Pipeline stage MKMLizer completed in 70.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-8b-calmtu-5756-v2
Waiting for inference service hastagaras-lm3-8b-calmtu-5756-v2 to be ready
Inference service hastagaras-lm3-8b-calmtu-5756-v2 ready after 40.3252956867218s
Pipeline stage ISVCDeployer completed in 49.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2971394062042236s
Received healthy response to inference request in 1.3391046524047852s
Received healthy response to inference request in 1.283808946609497s
Received healthy response to inference request in 3.8805646896362305s
Received healthy response to inference request in 1.3633198738098145s
5 requests
0 failed requests
5th percentile: 1.2948680877685548
10th percentile: 1.3059272289276123
20th percentile: 1.3280455112457275
30th percentile: 1.343947696685791
40th percentile: 1.3536337852478026
50th percentile: 1.3633198738098145
60th percentile: 1.736847686767578
70th percentile: 2.1103754997253414
80th percentile: 2.613824462890625
90th percentile: 3.247194576263428
95th percentile: 3.563879632949829
99th percentile: 3.8172276782989503
mean time: 2.0327875137329103
Pipeline stage StressChecker completed in 10.90s
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
hastagaras-lm3-8b-calmtu_5756_v2 status is now deployed due to DeploymentManager action
hastagaras-lm3-8b-calmtu_5756_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-8b-calmtu_5756_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-calmtu-5756-v2 is running
Tearing down inference service hastagaras-lm3-8b-calmtu-5756-v2
Toredown service hastagaras-lm3-8b-calmtu-5756-v2
Pipeline stage ISVCDeleter completed in 3.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-calmtu-5756-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.79s
hastagaras-lm3-8b-calmtu_5756_v2 status is now torndown due to DeploymentManager action