developer_uid: helkero
submission_id: kaoeiri-perpicon-experim_1827_v1
model_name: test1-perpicon
model_group: Kaoeiri/Perpicon-Experim
status: torndown
timestamp: 2024-06-10T01:09:33+00:00
num_battles: 14318
num_wins: 6940
celo_rating: 1169.93
family_friendly_score: 0.0
submission_type: basic
model_repo: Kaoeiri/Perpicon-Experimental-1
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: test1-perpicon
is_internal_developer: False
language_model: Kaoeiri/Perpicon-Experimental-1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-09
win_ratio: 0.4847045676770499
generation_params: {'temperature': 1.17, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 1000, '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-1827-v1-mkmlizer
Waiting for job on kaoeiri-perpicon-experim-1827-v1-mkmlizer to finish
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ _____ __ __ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ /___/ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ Version: 0.8.14 ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ https://mk1.ai ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ The license key for the current software has been verified as ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ belonging to: ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ Chai Research Corp. ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ║ ║
kaoeiri-perpicon-experim-1827-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-perpicon-experim-1827-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.
kaoeiri-perpicon-experim-1827-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Downloaded to shared memory in 104.726s
kaoeiri-perpicon-experim-1827-v1-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:05, 49.34it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:04, 65.76it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:03, 72.86it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:05, 43.23it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:05, 45.29it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:04, 54.58it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:03, 61.73it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:03, 67.51it/s] Loading 0: 25%|██▌ | 74/291 [00:01<00:03, 69.02it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 42.00it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:03, 50.20it/s] Loading 0: 34%|███▍ | 100/291 [00:01<00:03, 57.56it/s] Loading 0: 37%|███▋ | 109/291 [00:01<00:02, 63.74it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:02, 75.16it/s] Loading 0: 45%|████▌ | 131/291 [00:02<00:02, 78.18it/s] Loading 0: 48%|████▊ | 140/291 [00:02<00:03, 46.39it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 53.44it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:02, 60.10it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 66.22it/s] Loading 0: 60%|██████ | 176/291 [00:02<00:01, 71.16it/s] Loading 0: 64%|██████▍ | 186/291 [00:03<00:01, 54.04it/s] Loading 0: 66%|██████▋ | 193/291 [00:03<00:01, 52.76it/s] Loading 0: 70%|██████▉ | 203/291 [00:03<00:01, 59.17it/s] Loading 0: 73%|███████▎ | 212/291 [00:03<00:01, 65.60it/s] Loading 0: 76%|███████▌ | 221/291 [00:03<00:00, 70.66it/s] Loading 0: 80%|████████ | 233/291 [00:04<00:01, 53.45it/s] Loading 0: 82%|████████▏ | 240/291 [00:04<00:00, 55.06it/s] Loading 0: 85%|████████▌ | 248/291 [00:04<00:00, 59.71it/s] Loading 0: 88%|████████▊ | 257/291 [00:04<00:00, 66.55it/s] Loading 0: 91%|█████████▏| 266/291 [00:04<00:00, 72.23it/s] Loading 0: 95%|█████████▍| 275/291 [00:04<00:00, 76.37it/s] Loading 0: 98%|█████████▊| 286/291 [00:10<00:00, 5.44it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-perpicon-experim-1827-v1-mkmlizer: quantized model in 24.704s
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Processed model Kaoeiri/Perpicon-Experimental-1 in 134.504s
kaoeiri-perpicon-experim-1827-v1-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-perpicon-experim-1827-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-perpicon-experim-1827-v1
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-1827-v1/special_tokens_map.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-1827-v1/tokenizer.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-1827-v1/tokenizer_config.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-perpicon-experim-1827-v1/config.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-perpicon-experim-1827-v1/flywheel_model.0.safetensors
kaoeiri-perpicon-experim-1827-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-perpicon-experim-1827-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.
kaoeiri-perpicon-experim-1827-v1-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-1827-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.
kaoeiri-perpicon-experim-1827-v1-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-1827-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.
kaoeiri-perpicon-experim-1827-v1-mkmlizer: warnings.warn(
kaoeiri-perpicon-experim-1827-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()
kaoeiri-perpicon-experim-1827-v1-mkmlizer: return self.fget.__get__(instance, owner)()
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Saving duration: 0.421s
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.688s
kaoeiri-perpicon-experim-1827-v1-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-perpicon-experim-1827-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-perpicon-experim-1827-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/config.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/merges.txt
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/special_tokens_map.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/tokenizer_config.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/vocab.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/tokenizer.json
kaoeiri-perpicon-experim-1827-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-perpicon-experim-1827-v1_reward/reward.tensors
Job kaoeiri-perpicon-experim-1827-v1-mkmlizer completed after 165.21s with status: succeeded
Stopping job with name kaoeiri-perpicon-experim-1827-v1-mkmlizer
Pipeline stage MKMLizer completed in 169.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-perpicon-experim-1827-v1
Waiting for inference service kaoeiri-perpicon-experim-1827-v1 to be ready
Inference service kaoeiri-perpicon-experim-1827-v1 ready after 482.8068759441376s
Pipeline stage ISVCDeployer completed in 490.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8446269035339355s
Received healthy response to inference request in 1.2074971199035645s
Received healthy response to inference request in 1.225027322769165s
Received healthy response to inference request in 1.1959142684936523s
Received healthy response to inference request in 1.1214752197265625s
5 requests
0 failed requests
5th percentile: 1.1363630294799805
10th percentile: 1.1512508392333984
20th percentile: 1.1810264587402344
30th percentile: 1.1982308387756349
40th percentile: 1.2028639793395997
50th percentile: 1.2074971199035645
60th percentile: 1.2145092010498046
70th percentile: 1.2215212821960448
80th percentile: 1.3489472389221193
90th percentile: 1.5967870712280274
95th percentile: 1.7207069873809813
99th percentile: 1.8198429203033446
mean time: 1.318908166885376
Pipeline stage StressChecker completed in 7.27s
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_1827_v1 status is now deployed due to DeploymentManager action
kaoeiri-perpicon-experim_1827_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of kaoeiri-perpicon-experim_1827_v1
Running pipeline stage ISVCDeleter
Checking if service kaoeiri-perpicon-experim-1827-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.37s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-1827-v1/config.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-1827-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-1827-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-1827-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-experim-1827-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-experim-1827-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.65s
kaoeiri-perpicon-experim_1827_v1 status is now torndown due to DeploymentManager action