developer_uid: sao10k
submission_id: setiaku-run1-dare-ties_v2
model_name: L3-Run-2-Formatted-Test
model_group: Setiaku/Run1-Dare-Ties
status: torndown
timestamp: 2024-05-28T15:31:48+00:00
num_battles: 14054
num_wins: 7484
celo_rating: 1198.91
family_friendly_score: 0.0
submission_type: basic
model_repo: Setiaku/Run1-Dare-Ties
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: L3-Run-2-Formatted-Test
is_internal_developer: False
language_model: Setiaku/Run1-Dare-Ties
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-28
win_ratio: 0.5325174327593568
generation_params: {'temperature': 1.22, 'top_p': 1.0, 'min_p': 0.065, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n,', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': 'Example Conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>[{user_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n', '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': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name setiaku-run1-dare-ties-v2-mkmlizer
Waiting for job on setiaku-run1-dare-ties-v2-mkmlizer to finish
setiaku-run1-dare-ties-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
setiaku-run1-dare-ties-v2-mkmlizer: ║     _____            __           __                                ║
setiaku-run1-dare-ties-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
setiaku-run1-dare-ties-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
setiaku-run1-dare-ties-v2-mkmlizer: ║       /___/                                                         ║
setiaku-run1-dare-ties-v2-mkmlizer: ║                                                                     ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  https://mk1.ai                                                     ║
setiaku-run1-dare-ties-v2-mkmlizer: ║                                                                     ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  belonging to:                                                      ║
setiaku-run1-dare-ties-v2-mkmlizer: ║                                                                     ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  Chai Research Corp.                                                ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
setiaku-run1-dare-ties-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
setiaku-run1-dare-ties-v2-mkmlizer: ║                                                                     ║
setiaku-run1-dare-ties-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
setiaku-run1-dare-ties-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.
setiaku-run1-dare-ties-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
setiaku-run1-dare-ties-v2-mkmlizer: Downloaded to shared memory in 201.641s
setiaku-run1-dare-ties-v2-mkmlizer: quantizing model to /dev/shm/model_cache
setiaku-run1-dare-ties-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
setiaku-run1-dare-ties-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:28,  2.38s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:17,  3.59it/s]
Loading 0:   8%|▊         | 23/291 [00:04<00:36,  7.40it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:20, 12.33it/s]
Loading 0:  17%|█▋        | 49/291 [00:05<00:10, 22.62it/s]
Loading 0:  21%|██        | 60/291 [00:05<00:10, 22.95it/s]
Loading 0:  24%|██▎       | 69/291 [00:05<00:07, 28.61it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 38.66it/s]
Loading 0:  32%|███▏      | 94/291 [00:05<00:03, 51.12it/s]
Loading 0:  36%|███▌      | 105/291 [00:06<00:03, 59.31it/s]
Loading 0:  42%|████▏     | 121/291 [00:06<00:02, 77.14it/s]
Loading 0:  46%|████▌     | 133/291 [00:06<00:01, 80.08it/s]
Loading 0:  51%|█████     | 148/291 [00:06<00:01, 91.61it/s]
Loading 0:  55%|█████▍    | 160/291 [00:06<00:01, 84.74it/s]
Loading 0:  59%|█████▉    | 171/291 [00:07<00:02, 54.79it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 66.72it/s]
Loading 0:  67%|██████▋   | 194/291 [00:07<00:01, 70.49it/s]
Loading 0:  71%|███████   | 207/291 [00:07<00:01, 82.16it/s]
Loading 0:  76%|███████▌  | 221/291 [00:07<00:00, 91.39it/s]
Loading 0:  80%|████████  | 234/291 [00:07<00:00, 99.74it/s]
Loading 0:  85%|████████▍ | 247/291 [00:07<00:00, 103.42it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 104.56it/s]
Loading 0:  93%|█████████▎| 271/291 [00:08<00:00, 64.05it/s] 
Loading 0:  96%|█████████▌| 280/291 [00:08<00:00, 67.28it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
setiaku-run1-dare-ties-v2-mkmlizer: quantized model in 24.494s
setiaku-run1-dare-ties-v2-mkmlizer: Processed model Setiaku/Run1-Dare-Ties in 228.895s
setiaku-run1-dare-ties-v2-mkmlizer: creating bucket guanaco-mkml-models
setiaku-run1-dare-ties-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
setiaku-run1-dare-ties-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/setiaku-run1-dare-ties-v2
setiaku-run1-dare-ties-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/setiaku-run1-dare-ties-v2/special_tokens_map.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/setiaku-run1-dare-ties-v2/config.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/setiaku-run1-dare-ties-v2/tokenizer_config.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/setiaku-run1-dare-ties-v2/tokenizer.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/setiaku-run1-dare-ties-v2/flywheel_model.0.safetensors
setiaku-run1-dare-ties-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
setiaku-run1-dare-ties-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.
setiaku-run1-dare-ties-v2-mkmlizer:   warnings.warn(
setiaku-run1-dare-ties-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.
setiaku-run1-dare-ties-v2-mkmlizer:   warnings.warn(
setiaku-run1-dare-ties-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.
setiaku-run1-dare-ties-v2-mkmlizer:   warnings.warn(
setiaku-run1-dare-ties-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()
setiaku-run1-dare-ties-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
setiaku-run1-dare-ties-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
setiaku-run1-dare-ties-v2-mkmlizer: Saving duration: 0.582s
setiaku-run1-dare-ties-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 147.943s
setiaku-run1-dare-ties-v2-mkmlizer: creating bucket guanaco-reward-models
setiaku-run1-dare-ties-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
setiaku-run1-dare-ties-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/setiaku-run1-dare-ties-v2_reward
setiaku-run1-dare-ties-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/setiaku-run1-dare-ties-v2_reward/config.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/setiaku-run1-dare-ties-v2_reward/tokenizer_config.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/setiaku-run1-dare-ties-v2_reward/tokenizer.json
setiaku-run1-dare-ties-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/setiaku-run1-dare-ties-v2_reward/reward.tensors
Job setiaku-run1-dare-ties-v2-mkmlizer completed after 434.48s with status: succeeded
Stopping job with name setiaku-run1-dare-ties-v2-mkmlizer
Pipeline stage MKMLizer completed in 436.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service setiaku-run1-dare-ties-v2
Waiting for inference service setiaku-run1-dare-ties-v2 to be ready
Inference service setiaku-run1-dare-ties-v2 ready after 50.39813423156738s
Pipeline stage ISVCDeployer completed in 57.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2575385570526123s
Received healthy response to inference request in 1.2975292205810547s
Received healthy response to inference request in 1.2816886901855469s
Received healthy response to inference request in 1.2571930885314941s
Received healthy response to inference request in 1.325608491897583s
5 requests
0 failed requests
5th percentile: 1.2620922088623048
10th percentile: 1.2669913291931152
20th percentile: 1.2767895698547362
30th percentile: 1.2848567962646484
40th percentile: 1.2911930084228516
50th percentile: 1.2975292205810547
60th percentile: 1.308760929107666
70th percentile: 1.3199926376342774
80th percentile: 1.511994504928589
90th percentile: 1.8847665309906008
95th percentile: 2.071152544021606
99th percentile: 2.220261354446411
mean time: 1.4839116096496583
Pipeline stage StressChecker completed in 8.02s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
setiaku-run1-dare-ties_v2 status is now deployed due to DeploymentManager action
setiaku-run1-dare-ties_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of setiaku-run1-dare-ties_v2
Running pipeline stage ISVCDeleter
Checking if service setiaku-run1-dare-ties-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key setiaku-run1-dare-ties-v2/config.json from bucket guanaco-mkml-models
Deleting key setiaku-run1-dare-ties-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key setiaku-run1-dare-ties-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key setiaku-run1-dare-ties-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key setiaku-run1-dare-ties-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key setiaku-run1-dare-ties-v2_reward/config.json from bucket guanaco-reward-models
Deleting key setiaku-run1-dare-ties-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key setiaku-run1-dare-ties-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key setiaku-run1-dare-ties-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key setiaku-run1-dare-ties-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key setiaku-run1-dare-ties-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key setiaku-run1-dare-ties-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.73s
setiaku-run1-dare-ties_v2 status is now torndown due to DeploymentManager action