developer_uid: helkero
submission_id: kaoeiri-perpicon-experim_5756_v3
model_name: Perpicon-temp-probe-testing-3
model_group: Kaoeiri/Perpicon-Experim
status: torndown
timestamp: 2024-06-12T03:44:46+00:00
num_battles: 16689
num_wins: 8610
celo_rating: 1179.04
family_friendly_score: 0.0
submission_type: basic
model_repo: Kaoeiri/Perpicon-Experimental-4
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: Perpicon-temp-probe-testing-3
is_internal_developer: False
language_model: Kaoeiri/Perpicon-Experimental-4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-11
win_ratio: 0.51590868236563
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.007, '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}
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 kaoeiri-perpicon-experim-5756-v3-mkmlizer
Waiting for job on kaoeiri-perpicon-experim-5756-v3-mkmlizer to finish
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ _____ __ __ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ /___/ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ Version: 0.8.14 ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ https://mk1.ai ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ The license key for the current software has been verified as ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ belonging to: ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ Chai Research Corp. ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-perpicon-experim-5756-v3-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-perpicon-experim-5756-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Downloaded to shared memory in 12.602s
kaoeiri-perpicon-experim-5756-v3-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:32, 1.98s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:34, 7.78it/s] Loading 0: 16%|█▌ | 46/291 [00:04<00:13, 18.26it/s] Loading 0: 23%|██▎ | 68/291 [00:04<00:07, 30.92it/s] Loading 0: 31%|███▏ | 91/291 [00:04<00:04, 47.31it/s] Loading 0: 39%|███▉ | 113/291 [00:04<00:02, 65.17it/s] Loading 0: 46%|████▌ | 134/291 [00:04<00:02, 56.39it/s] Loading 0: 54%|█████▍ | 157/291 [00:05<00:01, 75.33it/s] Loading 0: 61%|██████ | 177/291 [00:05<00:01, 91.24it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:00, 116.21it/s] Loading 0: 76%|███████▋ | 222/291 [00:05<00:00, 130.59it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 154.82it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 164.34it/s] Loading 0: 99%|█████████▉| 289/291 [00:06<00:00, 94.10it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-perpicon-experim-5756-v3-mkmlizer: quantized model in 16.915s
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Processed model Kaoeiri/Perpicon-Experimental-4 in 30.413s
kaoeiri-perpicon-experim-5756-v3-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-perpicon-experim-5756-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v3
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v3/config.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v3/special_tokens_map.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v3/tokenizer_config.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v3/tokenizer.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v3/flywheel_model.0.safetensors
kaoeiri-perpicon-experim-5756-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-perpicon-experim-5756-v3-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-perpicon-experim-5756-v3-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-v3-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-perpicon-experim-5756-v3-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-v3-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-perpicon-experim-5756-v3-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-v3-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-perpicon-experim-5756-v3-mkmlizer: return self.fget.__get__(instance, owner)()
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Saving duration: 0.227s
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.104s
kaoeiri-perpicon-experim-5756-v3-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-perpicon-experim-5756-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-perpicon-experim-5756-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/config.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/special_tokens_map.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/merges.txt
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/vocab.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/tokenizer_config.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/tokenizer.json
kaoeiri-perpicon-experim-5756-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v3_reward/reward.tensors
Job kaoeiri-perpicon-experim-5756-v3-mkmlizer completed after 62.85s with status: succeeded
Stopping job with name kaoeiri-perpicon-experim-5756-v3-mkmlizer
Pipeline stage MKMLizer completed in 66.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-perpicon-experim-5756-v3
Waiting for inference service kaoeiri-perpicon-experim-5756-v3 to be ready
Failed to get response for submission cycy233-misllm-v6-8-1-5_v1: ('http://cycy233-misllm-v6-8-1-5-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51534->127.0.0.1:8080: read: connection reset by peer\n')
Inference service kaoeiri-perpicon-experim-5756-v3 ready after 40.44010019302368s
Pipeline stage ISVCDeployer completed in 47.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1536738872528076s
Received healthy response to inference request in 1.2702229022979736s
Received healthy response to inference request in 1.2530906200408936s
Received healthy response to inference request in 1.219233512878418s
Received healthy response to inference request in 1.0939478874206543s
5 requests
0 failed requests
5th percentile: 1.119005012512207
10th percentile: 1.1440621376037599
20th percentile: 1.1941763877868652
30th percentile: 1.2260049343109132
40th percentile: 1.2395477771759034
50th percentile: 1.2530906200408936
60th percentile: 1.2599435329437256
70th percentile: 1.2667964458465577
80th percentile: 1.4469130992889405
90th percentile: 1.800293493270874
95th percentile: 1.9769836902618407
99th percentile: 2.118335847854614
mean time: 1.3980337619781493
Pipeline stage StressChecker completed in 7.71s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
kaoeiri-perpicon-experim_5756_v3 status is now deployed due to DeploymentManager action
kaoeiri-perpicon-experim_5756_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of kaoeiri-perpicon-experim_5756_v3
Running pipeline stage ISVCDeleter
Checking if service kaoeiri-perpicon-experim-5756-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-5756-v3/config.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.96s
kaoeiri-perpicon-experim_5756_v3 status is now torndown due to DeploymentManager action