setiaku-run2-modelstock

submission_id: setiaku-run2-modelstock_v1

developer_uid: sao10k

best_of: 16

celo_rating: 1191.94

display_name: L3-Run-1-Formatted-Test

family_friendly_score: 0.0

formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.', '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}

generation_params: {'temperature': 1.17, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 40, '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}

is_internal_developer: False

language_model: Setiaku/Run2-ModelStock

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Setiaku/Run2-ModelStock

model_name: L3-Run-1-Formatted-Test

model_num_parameters: 8030261248.0

model_repo: Setiaku/Run2-ModelStock

model_size: 8B

num_battles: 6950

num_wins: 3622

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-05-28T11:59:48+00:00

us_pacific_date: 2024-05-28

win_ratio: 0.5211510791366907

Resubmit model

Running pipeline stage MKMLizer
Starting job with name setiaku-run2-modelstock-v1-mkmlizer
Waiting for job on setiaku-run2-modelstock-v1-mkmlizer to finish
setiaku-run2-modelstock-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
setiaku-run2-modelstock-v1-mkmlizer: ║     _____            __           __                                ║
setiaku-run2-modelstock-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
setiaku-run2-modelstock-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
setiaku-run2-modelstock-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
setiaku-run2-modelstock-v1-mkmlizer: ║       /___/                                                         ║
setiaku-run2-modelstock-v1-mkmlizer: ║                                                                     ║
setiaku-run2-modelstock-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
setiaku-run2-modelstock-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
setiaku-run2-modelstock-v1-mkmlizer: ║  https://mk1.ai                                                     ║
setiaku-run2-modelstock-v1-mkmlizer: ║                                                                     ║
setiaku-run2-modelstock-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
setiaku-run2-modelstock-v1-mkmlizer: ║  belonging to:                                                      ║
setiaku-run2-modelstock-v1-mkmlizer: ║                                                                     ║
setiaku-run2-modelstock-v1-mkmlizer: ║  Chai Research Corp.                                                ║
setiaku-run2-modelstock-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
setiaku-run2-modelstock-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
setiaku-run2-modelstock-v1-mkmlizer: ║                                                                     ║
setiaku-run2-modelstock-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Retrying (%r) after connection broken by '%r': %s
setiaku-run2-modelstock-v1-mkmlizer: Downloaded to shared memory in 76.069s
setiaku-run2-modelstock-v1-mkmlizer: quantizing model to /dev/shm/model_cache
setiaku-run2-modelstock-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
setiaku-run2-modelstock-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:39,  2.42s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:18,  3.54it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:34,  7.66it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:16, 15.58it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:10, 21.84it/s]
Loading 0:  21%|██        | 61/291 [00:05<00:10, 22.17it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 33.35it/s]
Loading 0:  30%|██▉       | 87/291 [00:05<00:04, 41.39it/s]
Loading 0:  35%|███▌      | 103/291 [00:06<00:03, 56.60it/s]
Loading 0:  39%|███▉      | 114/291 [00:06<00:02, 63.46it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:02, 79.36it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 84.21it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 96.57it/s]
Loading 0:  58%|█████▊    | 169/291 [00:06<00:02, 59.95it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 73.35it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 77.87it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 93.56it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 97.15it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 106.75it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 106.86it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 112.00it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 66.99it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
setiaku-run2-modelstock-v1-mkmlizer: quantized model in 24.508s
setiaku-run2-modelstock-v1-mkmlizer: Processed model Setiaku/Run2-ModelStock in 103.947s
setiaku-run2-modelstock-v1-mkmlizer: creating bucket guanaco-mkml-models
setiaku-run2-modelstock-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
setiaku-run2-modelstock-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/setiaku-run2-modelstock-v1
setiaku-run2-modelstock-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v1/config.json
setiaku-run2-modelstock-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v1/special_tokens_map.json
setiaku-run2-modelstock-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v1/tokenizer_config.json
setiaku-run2-modelstock-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/setiaku-run2-modelstock-v1/tokenizer.json
setiaku-run2-modelstock-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/setiaku-run2-modelstock-v1/flywheel_model.0.safetensors
setiaku-run2-modelstock-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v1-mkmlizer:   warnings.warn(
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v1-mkmlizer:   warnings.warn(
setiaku-run2-modelstock-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.
setiaku-run2-modelstock-v1-mkmlizer:   warnings.warn(
setiaku-run2-modelstock-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()
setiaku-run2-modelstock-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
setiaku-run2-modelstock-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
setiaku-run2-modelstock-v1-mkmlizer: Saving duration: 0.459s
setiaku-run2-modelstock-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.427s
setiaku-run2-modelstock-v1-mkmlizer: creating bucket guanaco-reward-models
setiaku-run2-modelstock-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
setiaku-run2-modelstock-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/tokenizer_config.json
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/special_tokens_map.json
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/vocab.json
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/config.json
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/merges.txt
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/tokenizer.json
setiaku-run2-modelstock-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/setiaku-run2-modelstock-v1_reward/reward.tensors
Job setiaku-run2-modelstock-v1-mkmlizer completed after 134.17s with status: succeeded
Stopping job with name setiaku-run2-modelstock-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service setiaku-run2-modelstock-v1
Waiting for inference service setiaku-run2-modelstock-v1 to be ready
Inference service setiaku-run2-modelstock-v1 ready after 100.51610684394836s
Pipeline stage ISVCDeployer completed in 106.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.180687427520752s
Received healthy response to inference request in 1.249403953552246s
Received healthy response to inference request in 1.331552267074585s
Received healthy response to inference request in 1.320129632949829s
Received healthy response to inference request in 1.3042876720428467s
5 requests
0 failed requests
5th percentile: 1.2603806972503662
10th percentile: 1.2713574409484862
20th percentile: 1.2933109283447266
30th percentile: 1.3074560642242432
40th percentile: 1.313792848587036
50th percentile: 1.320129632949829
60th percentile: 1.3246986865997314
70th percentile: 1.3292677402496338
80th percentile: 1.5013792991638186
90th percentile: 1.8410333633422853
95th percentile: 2.0108603954315183
99th percentile: 2.146722021102905
mean time: 1.4772121906280518
Pipeline stage StressChecker completed in 8.05s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-run2-modelstock_v1 status is now deployed due to DeploymentManager action
setiaku-run2-modelstock_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of setiaku-run2-modelstock_v1
Running pipeline stage ISVCDeleter
Checking if service setiaku-run2-modelstock-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key setiaku-run2-modelstock-v1/config.json from bucket guanaco-mkml-models
Deleting key setiaku-run2-modelstock-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key setiaku-run2-modelstock-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key setiaku-run2-modelstock-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key setiaku-run2-modelstock-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key setiaku-run2-modelstock-v1_reward/config.json from bucket guanaco-reward-models
Deleting key setiaku-run2-modelstock-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key setiaku-run2-modelstock-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key setiaku-run2-modelstock-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key setiaku-run2-modelstock-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key setiaku-run2-modelstock-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key setiaku-run2-modelstock-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.03s
setiaku-run2-modelstock_v1 status is now torndown due to DeploymentManager action