kaoeiri-pantheramix-l3-r_5669

submission_id: kaoeiri-pantheramix-l3-r_5669_v9

developer_uid: helkero

best_of: 16

celo_rating: 1212.38

display_name: kaoeiri-pantheramix-l3-r_5669_v9

family_friendly_score: 0.0

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': 'Example conversation:\n{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}

generation_params: {'temperature': 1.0, '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}

is_internal_developer: False

language_model: Kaoeiri/PantheraMix-L3-RP-TestProbe-3X

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Kaoeiri/PantheraMix-L3-R

model_name: kaoeiri-pantheramix-l3-r_5669_v9

model_num_parameters: 8030261248.0

model_repo: Kaoeiri/PantheraMix-L3-RP-TestProbe-3X

model_size: 8B

num_battles: 25267

num_wins: 13763

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-06-18T23:02:54+00:00

us_pacific_date: 2024-06-18

win_ratio: 0.5447025764831599

Resubmit model

Running pipeline stage MKMLizer
Starting job with name kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer
Waiting for job on kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer to finish
Failed to get response for submission undi95-meta-llama-3-70b-_6209_v4: ('http://undi95-meta-llama-3-70b-6209-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'pending request queue full\n')
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║     _____            __           __                                ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║       /___/                                                         ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║                                                                     ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  Version: 0.8.14                                                    ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  https://mk1.ai                                                     ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║                                                                     ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  belonging to:                                                      ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║                                                                     ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  Chai Research Corp.                                                ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ║                                                                     ║
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-pantheramix-l3-r-5669-v9-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.
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer:   warnings.warn(warning_message, FutureWarning)
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Downloaded to shared memory in 17.487s
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission undi95-meta-llama-3-70b-_6209_v4: ('http://undi95-meta-llama-3-70b-6209-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'pending request queue full\n')
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:13,  2.12s/it]
Loading 0:   5%|▌         | 15/291 [00:04<00:59,  4.68it/s]
Loading 0:  11%|█         | 32/291 [00:04<00:21, 11.99it/s]
Loading 0:  17%|█▋        | 49/291 [00:04<00:11, 21.33it/s]
Loading 0:  22%|██▏       | 64/291 [00:04<00:07, 31.30it/s]
Loading 0:  27%|██▋       | 78/291 [00:04<00:05, 41.84it/s]
Loading 0:  33%|███▎      | 95/291 [00:04<00:03, 57.43it/s]
Loading 0:  38%|███▊      | 112/291 [00:04<00:02, 73.94it/s]
Loading 0:  44%|████▍     | 128/291 [00:05<00:01, 88.51it/s]
Loading 0:  49%|████▉     | 144/291 [00:05<00:01, 100.14it/s]
Loading 0:  55%|█████▍    | 159/291 [00:05<00:01, 107.80it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:02, 53.56it/s] 
Loading 0:  64%|██████▍   | 186/291 [00:06<00:01, 61.44it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:01, 78.14it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 94.56it/s]
Loading 0:  81%|████████  | 235/291 [00:06<00:00, 105.64it/s]
Loading 0:  86%|████████▌ | 250/291 [00:06<00:00, 113.63it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 124.11it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 134.40it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: quantized model in 20.003s
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Processed model Kaoeiri/PantheraMix-L3-RP-TestProbe-3X in 38.608s
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-pantheramix-l3-r-5669-v9
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-pantheramix-l3-r-5669-v9/config.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-pantheramix-l3-r-5669-v9/special_tokens_map.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-pantheramix-l3-r-5669-v9/tokenizer_config.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-pantheramix-l3-r-5669-v9/tokenizer.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-pantheramix-l3-r-5669-v9/flywheel_model.0.safetensors
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-pantheramix-l3-r-5669-v9-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.
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer:   warnings.warn(
kaoeiri-pantheramix-l3-r-5669-v9-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.
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer:   warnings.warn(
kaoeiri-pantheramix-l3-r-5669-v9-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.
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer:   warnings.warn(
kaoeiri-pantheramix-l3-r-5669-v9-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()
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer:   return self.fget.__get__(instance, owner)()
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Saving duration: 0.309s
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.061s
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/special_tokens_map.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/config.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/tokenizer_config.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/merges.txt
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/vocab.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/tokenizer.json
kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-pantheramix-l3-r-5669-v9_reward/reward.tensors
Job kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer completed after 136.07s with status: succeeded
Stopping job with name kaoeiri-pantheramix-l3-r-5669-v9-mkmlizer
Pipeline stage MKMLizer completed in 138.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-pantheramix-l3-r-5669-v9
Waiting for inference service kaoeiri-pantheramix-l3-r-5669-v9 to be ready
Failed to get response for submission undi95-meta-llama-3-70b-_6209_v4: ('http://undi95-meta-llama-3-70b-6209-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service kaoeiri-pantheramix-l3-r-5669-v9 ready after 40.30094838142395s
Pipeline stage ISVCDeployer completed in 47.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.261005401611328s
Received healthy response to inference request in 1.3231241703033447s
Failed to get response for submission undi95-meta-llama-3-70b-_6209_v4: ('http://undi95-meta-llama-3-70b-6209-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 1.2788994312286377s
Received healthy response to inference request in 1.3538684844970703s
Received healthy response to inference request in 1.3141918182373047s
5 requests
0 failed requests
5th percentile: 1.2859579086303712
10th percentile: 1.2930163860321044
20th percentile: 1.3071333408355712
30th percentile: 1.3159782886505127
40th percentile: 1.3195512294769287
50th percentile: 1.3231241703033447
60th percentile: 1.335421895980835
70th percentile: 1.3477196216583252
80th percentile: 1.535295867919922
90th percentile: 1.8981506347656252
95th percentile: 2.079578018188476
99th percentile: 2.2247199249267577
mean time: 1.506217861175537
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
kaoeiri-pantheramix-l3-r_5669_v9 status is now deployed due to DeploymentManager action
kaoeiri-pantheramix-l3-r_5669_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of kaoeiri-pantheramix-l3-r_5669_v9
Running pipeline stage ISVCDeleter
Checking if service kaoeiri-pantheramix-l3-r-5669-v9 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.42s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key kaoeiri-pantheramix-l3-r-5669-v9/config.json from bucket guanaco-mkml-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/config.json from bucket guanaco-reward-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key kaoeiri-pantheramix-l3-r-5669-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.56s
kaoeiri-pantheramix-l3-r_5669_v9 status is now torndown due to DeploymentManager action