developer_uid: helkero
submission_id: kaoeiri-perpicon-experim_5756_v2
model_name: Perpicon-temp-probe-testing-2
model_group: Kaoeiri/Perpicon-Experim
status: torndown
timestamp: 2024-06-12T03:43:51+00:00
num_battles: 16937
num_wins: 8738
celo_rating: 1178.58
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-2
is_internal_developer: False
language_model: Kaoeiri/Perpicon-Experimental-4
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-11
win_ratio: 0.5159119088386374
generation_params: {'temperature': 0.74, 'top_p': 1.0, 'min_p': 0.01, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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 kaoeiri-perpicon-experim-5756-v2-mkmlizer
Waiting for job on kaoeiri-perpicon-experim-5756-v2-mkmlizer to finish
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ _____ __ __ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ /___/ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ Version: 0.8.14 ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ https://mk1.ai ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ The license key for the current software has been verified as ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ belonging to: ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ Chai Research Corp. ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ║ ║
kaoeiri-perpicon-experim-5756-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-perpicon-experim-5756-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.
kaoeiri-perpicon-experim-5756-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Downloaded to shared memory in 16.592s
kaoeiri-perpicon-experim-5756-v2-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:13, 2.33s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:04, 4.28it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.37it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.45it/s] Loading 0: 24%|██▎ | 69/291 [00:05<00:07, 31.67it/s] Loading 0: 30%|██▉ | 86/291 [00:05<00:04, 44.37it/s] Loading 0: 36%|███▌ | 104/291 [00:05<00:03, 59.33it/s] Loading 0: 42%|████▏ | 122/291 [00:05<00:03, 48.01it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:02, 62.06it/s] Loading 0: 54%|█████▍ | 158/291 [00:06<00:01, 77.22it/s] Loading 0: 60%|██████ | 176/291 [00:06<00:01, 92.42it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:00, 106.87it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:00, 119.85it/s] Loading 0: 79%|███████▉ | 230/291 [00:06<00:00, 130.93it/s] Loading 0: 85%|████████▍ | 247/291 [00:06<00:00, 134.84it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 142.40it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 148.46it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-perpicon-experim-5756-v2-mkmlizer: quantized model in 23.560s
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Processed model Kaoeiri/Perpicon-Experimental-4 in 42.805s
kaoeiri-perpicon-experim-5756-v2-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-perpicon-experim-5756-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v2
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v2/config.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v2/special_tokens_map.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v2/tokenizer_config.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v2/tokenizer.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-perpicon-experim-5756-v2/flywheel_model.0.safetensors
kaoeiri-perpicon-experim-5756-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-perpicon-experim-5756-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.
kaoeiri-perpicon-experim-5756-v2-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-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.
kaoeiri-perpicon-experim-5756-v2-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-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.
kaoeiri-perpicon-experim-5756-v2-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-5756-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()
kaoeiri-perpicon-experim-5756-v2-mkmlizer: return self.fget.__get__(instance, owner)()
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Saving duration: 0.423s
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.897s
kaoeiri-perpicon-experim-5756-v2-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-perpicon-experim-5756-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-perpicon-experim-5756-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/config.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/tokenizer_config.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/vocab.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/merges.txt
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/special_tokens_map.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/tokenizer.json
kaoeiri-perpicon-experim-5756-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-perpicon-experim-5756-v2_reward/reward.tensors
Job kaoeiri-perpicon-experim-5756-v2-mkmlizer completed after 72.91s with status: succeeded
Stopping job with name kaoeiri-perpicon-experim-5756-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-perpicon-experim-5756-v2
Waiting for inference service kaoeiri-perpicon-experim-5756-v2 to be ready
Inference service kaoeiri-perpicon-experim-5756-v2 ready after 40.24823617935181s
Pipeline stage ISVCDeployer completed in 46.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.162400960922241s
Received healthy response to inference request in 1.2479197978973389s
Received healthy response to inference request in 1.2446582317352295s
Received healthy response to inference request in 1.2373037338256836s
Received healthy response to inference request in 1.2448995113372803s
5 requests
0 failed requests
5th percentile: 1.2387746334075929
10th percentile: 1.240245532989502
20th percentile: 1.2431873321533202
30th percentile: 1.2447064876556397
40th percentile: 1.24480299949646
50th percentile: 1.2448995113372803
60th percentile: 1.2461076259613038
70th percentile: 1.2473157405853272
80th percentile: 1.4308160305023194
90th percentile: 1.7966084957122803
95th percentile: 1.9795047283172607
99th percentile: 2.125821714401245
mean time: 1.4274364471435548
Pipeline stage StressChecker completed in 7.76s
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
kaoeiri-perpicon-experim_5756_v2 status is now deployed due to DeploymentManager action
kaoeiri-perpicon-experim_5756_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of kaoeiri-perpicon-experim_5756_v2
Running pipeline stage ISVCDeleter
Checking if service kaoeiri-perpicon-experim-5756-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-5756-v2/config.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-5756-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-5756-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.98s
kaoeiri-perpicon-experim_5756_v2 status is now torndown due to DeploymentManager action