developer_uid: Hastagaras
submission_id: hastagaras-lm3-8b-calmtu_5756_v1
model_name: calmtune-but-broken
model_group: Hastagaras/lm3-8b-calmtu
status: torndown
timestamp: 2024-05-11T09:08:41+00:00
num_battles: 20711
num_wins: 10662
celo_rating: 1188.78
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-but-broken
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: 0.514798899135725
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, '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're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", '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}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer
Waiting for job on hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer to finish
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Downloaded to shared memory in 26.619s
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:00, 146.59it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 37.53it/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-v1-mkmlizer: quantized model in 17.173s
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Processed model Hastagaras/lm3-8b-calmtune-broken in 44.784s
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v1
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v1/config.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v1/special_tokens_map.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v1/tokenizer.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v1/tokenizer_config.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-8b-calmtu-5756-v1/flywheel_model.0.safetensors
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-calmtu-5756-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.
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer:   warnings.warn(
Failed to get response for submission blend_dimun_2024-05-11: ('http://chaoticneutrals-poppy-po-3816-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
hastagaras-lm3-8b-calmtu-5756-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()
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Saving duration: 0.232s
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.039s
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/config.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/special_tokens_map.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/vocab.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/merges.txt
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/tokenizer_config.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/tokenizer.json
hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-8b-calmtu-5756-v1_reward/reward.tensors
Job hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer completed after 83.36s with status: succeeded
Stopping job with name hastagaras-lm3-8b-calmtu-5756-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-8b-calmtu-5756-v1
Waiting for inference service hastagaras-lm3-8b-calmtu-5756-v1 to be ready
Inference service hastagaras-lm3-8b-calmtu-5756-v1 ready after 40.21032214164734s
Pipeline stage ISVCDeployer completed in 47.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.230384349822998s
Received healthy response to inference request in 1.3160285949707031s
Received healthy response to inference request in 1.4437921047210693s
Received healthy response to inference request in 1.347823143005371s
Received healthy response to inference request in 1.327327013015747s
5 requests
0 failed requests
5th percentile: 1.3182882785797119
10th percentile: 1.3205479621887206
20th percentile: 1.3250673294067383
30th percentile: 1.331426239013672
40th percentile: 1.3396246910095215
50th percentile: 1.347823143005371
60th percentile: 1.3862107276916504
70th percentile: 1.4245983123779298
80th percentile: 1.6011105537414552
90th percentile: 1.9157474517822266
95th percentile: 2.073065900802612
99th percentile: 2.198920660018921
mean time: 1.5330710411071777
Pipeline stage StressChecker completed in 8.31s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-lm3-8b-calmtu_5756_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-lm3-8b-calmtu_5756_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-8b-calmtu_5756_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-calmtu-5756-v1 is running
Tearing down inference service hastagaras-lm3-8b-calmtu-5756-v1
Toredown service hastagaras-lm3-8b-calmtu-5756-v1
Pipeline stage ISVCDeleter completed in 12.07s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-calmtu-5756-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-calmtu-5756-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.14s
hastagaras-lm3-8b-calmtu_5756_v1 status is now torndown due to DeploymentManager action