kaoeiri-perpicon-l3-expe_1050

developer_uid: helkero

submission_id: kaoeiri-perpicon-l3-expe_1050_v6

model_name: kaoeiri-perpicon-l3-expe_1050_v6

model_group: Kaoeiri/Perpicon-L3-Expe

status: torndown

timestamp: 2024-06-25T21:32:22+00:00

num_battles: 18193

num_wins: 8666

celo_rating: 1166.99

family_friendly_score: 0.0

submission_type: basic

model_repo: Kaoeiri/Perpicon-L3-Experimental-3.5-Rewinded

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: kaoeiri-perpicon-l3-expe_1050_v6

is_internal_developer: False

language_model: Kaoeiri/Perpicon-L3-Experimental-3.5-Rewinded

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-25

win_ratio: 0.47633705271258175

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': 4, '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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer
Waiting for job on kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer to finish
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║     _____            __           __                                ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║       /___/                                                         ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║                                                                     ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  https://mk1.ai                                                     ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║                                                                     ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  belonging to:                                                      ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║                                                                     ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  Chai Research Corp.                                                ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ║                                                                     ║
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-perpicon-l3-expe-1050-v6-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-l3-expe-1050-v6-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Retrying (%r) after connection broken by '%r': %s
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Downloaded to shared memory in 33.190s
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:57,  2.28s/it]
Loading 0:   5%|▍         | 14/291 [00:04<01:08,  4.07it/s]
Loading 0:  11%|█         | 31/291 [00:04<00:23, 10.91it/s]
Loading 0:  14%|█▍        | 42/291 [00:04<00:15, 16.42it/s]
Loading 0:  20%|██        | 59/291 [00:04<00:08, 27.43it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:05, 40.31it/s]
Loading 0:  31%|███       | 90/291 [00:05<00:03, 51.43it/s]
Loading 0:  36%|███▌      | 104/291 [00:05<00:02, 63.40it/s]
Loading 0:  42%|████▏     | 121/291 [00:05<00:02, 79.31it/s]
Loading 0:  46%|████▋     | 135/291 [00:05<00:02, 52.87it/s]
Loading 0:  51%|█████     | 149/291 [00:06<00:02, 64.11it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 79.61it/s]
Loading 0:  62%|██████▏   | 179/291 [00:06<00:01, 88.16it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:00, 98.44it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:00, 110.93it/s]
Loading 0:  77%|███████▋  | 225/291 [00:06<00:00, 115.04it/s]
Loading 0:  82%|████████▏ | 239/291 [00:06<00:00, 117.81it/s]
Loading 0:  87%|████████▋ | 254/291 [00:06<00:00, 125.99it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 122.83it/s]
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 126.95it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: quantized model in 23.013s
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Processed model Kaoeiri/Perpicon-L3-Experimental-3.5-Rewinded in 58.710s
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-perpicon-l3-expe-1050-v6
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-perpicon-l3-expe-1050-v6/config.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-perpicon-l3-expe-1050-v6/tokenizer_config.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-perpicon-l3-expe-1050-v6/special_tokens_map.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-perpicon-l3-expe-1050-v6/tokenizer.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-perpicon-l3-expe-1050-v6/flywheel_model.0.safetensors
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-perpicon-l3-expe-1050-v6-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-l3-expe-1050-v6-mkmlizer:   warnings.warn(
kaoeiri-perpicon-l3-expe-1050-v6-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-l3-expe-1050-v6-mkmlizer:   warnings.warn(
kaoeiri-perpicon-l3-expe-1050-v6-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-l3-expe-1050-v6-mkmlizer:   warnings.warn(
kaoeiri-perpicon-l3-expe-1050-v6-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-l3-expe-1050-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Saving duration: 0.444s
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.592s
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/config.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/tokenizer_config.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/special_tokens_map.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/merges.txt
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/vocab.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/tokenizer.json
kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-perpicon-l3-expe-1050-v6_reward/reward.tensors
Job kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer completed after 125.1s with status: succeeded
Stopping job with name kaoeiri-perpicon-l3-expe-1050-v6-mkmlizer
Pipeline stage MKMLizer completed in 125.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-perpicon-l3-expe-1050-v6
Waiting for inference service kaoeiri-perpicon-l3-expe-1050-v6 to be ready
Inference service kaoeiri-perpicon-l3-expe-1050-v6 ready after 50.58483862876892s
Pipeline stage ISVCDeployer completed in 56.74s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0918712615966797s
Received healthy response to inference request in 1.1541013717651367s
Received healthy response to inference request in 1.1640195846557617s
Received healthy response to inference request in 1.178602695465088s
Received healthy response to inference request in 1.191629409790039s
5 requests
0 failed requests
5th percentile: 1.1560850143432617
10th percentile: 1.1580686569213867
20th percentile: 1.1620359420776367
30th percentile: 1.166936206817627
40th percentile: 1.1727694511413573
50th percentile: 1.178602695465088
60th percentile: 1.1838133811950684
70th percentile: 1.189024066925049
80th percentile: 1.3716777801513673
90th percentile: 1.7317745208740236
95th percentile: 1.9118228912353514
99th percentile: 2.055861587524414
mean time: 1.356044864654541
Pipeline stage StressChecker completed in 7.71s
kaoeiri-perpicon-l3-expe_1050_v6 status is now deployed due to DeploymentManager action
kaoeiri-perpicon-l3-expe_1050_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of kaoeiri-perpicon-l3-expe_1050_v6
Running pipeline stage ISVCDeleter
Checking if service kaoeiri-perpicon-l3-expe-1050-v6 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-l3-expe-1050-v6/config.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key kaoeiri-perpicon-l3-expe-1050-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.25s
kaoeiri-perpicon-l3-expe_1050_v6 status is now torndown due to DeploymentManager action