developer_uid: Hastagaras
submission_id: hastagaras-esekmbrew-0-2_v1
model_name: huehe
model_group: Hastagaras/esekmbrew-0.2
status: torndown
timestamp: 2024-05-17T13:31:44+00:00
num_battles: 21562
num_wins: 11048
celo_rating: 1179.11
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/esekmbrew-0.2
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: huehe
is_internal_developer: False
language_model: Hastagaras/esekmbrew-0.2
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-17
win_ratio: 0.5123828958352658
generation_params: {'temperature': 0.95, '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': 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 hastagaras-esekmbrew-0-2-v1-mkmlizer
Waiting for job on hastagaras-esekmbrew-0-2-v1-mkmlizer to finish
hastagaras-esekmbrew-0-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║                                                                     ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║                                                                     ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║                                                                     ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ║                                                                     ║
hastagaras-esekmbrew-0-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekmbrew-0-2-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-esekmbrew-0-2-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-esekmbrew-0-2-v1-mkmlizer: Downloaded to shared memory in 27.198s
hastagaras-esekmbrew-0-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekmbrew-0-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekmbrew-0-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 177.52it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 195.11it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:01, 184.48it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 196.40it/s]
Loading 0:  35%|███▍      | 101/291 [00:00<00:02, 91.82it/s]
Loading 0:  42%|████▏     | 121/291 [00:00<00:01, 109.89it/s]
Loading 0:  49%|████▉     | 143/291 [00:01<00:01, 132.13it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:00, 151.83it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 97.25it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 107.80it/s]
Loading 0:  78%|███████▊  | 228/291 [00:01<00:00, 133.74it/s]
Loading 0:  85%|████████▌ | 248/291 [00:01<00:00, 144.90it/s]
Loading 0:  94%|█████████▍| 273/291 [00:01<00:00, 167.13it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekmbrew-0-2-v1-mkmlizer: quantized model in 17.764s
hastagaras-esekmbrew-0-2-v1-mkmlizer: Processed model Hastagaras/esekmbrew-0.2 in 46.045s
hastagaras-esekmbrew-0-2-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekmbrew-0-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekmbrew-0-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v1
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v1/config.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v1/tokenizer_config.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v1/special_tokens_map.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v1/tokenizer.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekmbrew-0-2-v1/flywheel_model.0.safetensors
hastagaras-esekmbrew-0-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekmbrew-0-2-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-esekmbrew-0-2-v1-mkmlizer:   warnings.warn(
hastagaras-esekmbrew-0-2-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-esekmbrew-0-2-v1-mkmlizer:   warnings.warn(
hastagaras-esekmbrew-0-2-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-esekmbrew-0-2-v1-mkmlizer:   warnings.warn(
hastagaras-esekmbrew-0-2-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-esekmbrew-0-2-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-esekmbrew-0-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekmbrew-0-2-v1-mkmlizer: Saving duration: 0.239s
hastagaras-esekmbrew-0-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.032s
hastagaras-esekmbrew-0-2-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekmbrew-0-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekmbrew-0-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/tokenizer_config.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/config.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/merges.txt
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/vocab.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/special_tokens_map.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/tokenizer.json
hastagaras-esekmbrew-0-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekmbrew-0-2-v1_reward/reward.tensors
Job hastagaras-esekmbrew-0-2-v1-mkmlizer completed after 73.75s with status: succeeded
Stopping job with name hastagaras-esekmbrew-0-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.24s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekmbrew-0-2-v1
Waiting for inference service hastagaras-esekmbrew-0-2-v1 to be ready
Inference service hastagaras-esekmbrew-0-2-v1 ready after 40.22587847709656s
Pipeline stage ISVCDeployer completed in 47.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.156620979309082s
Received healthy response to inference request in 1.2448804378509521s
Received healthy response to inference request in 1.2424256801605225s
Received healthy response to inference request in 1.2635130882263184s
Received healthy response to inference request in 1.1628632545471191s
5 requests
0 failed requests
5th percentile: 1.1787757396697998
10th percentile: 1.1946882247924804
20th percentile: 1.2265131950378418
30th percentile: 1.2429166316986084
40th percentile: 1.2438985347747802
50th percentile: 1.2448804378509521
60th percentile: 1.2523334980010987
70th percentile: 1.259786558151245
80th percentile: 1.4421346664428714
90th percentile: 1.7993778228759767
95th percentile: 1.977999401092529
99th percentile: 2.1208966636657713
mean time: 1.414060688018799
Pipeline stage StressChecker completed in 7.91s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-esekmbrew-0-2_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-esekmbrew-0-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-esekmbrew-0-2_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-esekmbrew-0-2-v1 is running
Tearing down inference service hastagaras-esekmbrew-0-2-v1
Toredown service hastagaras-esekmbrew-0-2-v1
Pipeline stage ISVCDeleter completed in 4.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-esekmbrew-0-2-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekmbrew-0-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-esekmbrew-0-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekmbrew-0-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekmbrew-0-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-esekmbrew-0-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekmbrew-0-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-esekmbrew-0-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-esekmbrew-0-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-esekmbrew-0-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-esekmbrew-0-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekmbrew-0-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.59s
hastagaras-esekmbrew-0-2_v1 status is now torndown due to DeploymentManager action