submission_id: kaoeiri-keiana-l3-test6-_7421_v1
developer_uid: helkero
status: inactive
model_repo: Kaoeiri/Keiana-L3-Test6.2-8B-18
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 0.9, '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}
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: {'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}
timestamp: 2024-06-09T01:54:19+00:00
model_name: kaoeiri-keiana-l3-test6-_7421_v1
model_eval_status: success
model_group: Kaoeiri/Keiana-L3-Test6.
num_battles: 7506
num_wins: 3980
celo_rating: 1202.35
safety_score: 0.97
propriety_score: 0.6723259762308998
propriety_total_count: 589.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: kaoeiri-keiana-l3-test6-_7421_v1
ineligible_reason: propriety_total_count < 5000
language_model: Kaoeiri/Keiana-L3-Test6.2-8B-18
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-08
win_ratio: 0.5302424726885159
Resubmit model
Running pipeline stage MKMLizer
Starting job with name kaoeiri-keiana-l3-test6-7421-v1-mkmlizer
Waiting for job on kaoeiri-keiana-l3-test6-7421-v1-mkmlizer to finish
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ _____ __ __ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ /___/ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ Version: 0.8.14 ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ https://mk1.ai ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ The license key for the current software has been verified as ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ belonging to: ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ Chai Research Corp. ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ║ ║
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
kaoeiri-keiana-l3-test6-7421-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-keiana-l3-test6-7421-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Downloaded to shared memory in 61.407s
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: quantizing model to /dev/shm/model_cache
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:44, 2.23s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:01, 4.46it/s] Loading 0: 8%|▊ | 23/291 [00:04<00:36, 7.36it/s] Loading 0: 14%|█▍ | 41/291 [00:04<00:14, 16.80it/s] Loading 0: 20%|██ | 59/291 [00:04<00:08, 28.49it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:06, 34.51it/s] Loading 0: 31%|███ | 89/291 [00:05<00:04, 49.17it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 53.72it/s] Loading 0: 42%|████▏ | 121/291 [00:05<00:02, 71.38it/s] Loading 0: 48%|████▊ | 139/291 [00:05<00:01, 88.99it/s] Loading 0: 53%|█████▎ | 154/291 [00:05<00:01, 81.28it/s] Loading 0: 59%|█████▉ | 171/291 [00:06<00:01, 97.35it/s] Loading 0: 64%|██████▎ | 185/291 [00:06<00:01, 85.40it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:00, 102.66it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:00, 117.70it/s] Loading 0: 81%|████████ | 236/291 [00:06<00:00, 98.04it/s] Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 112.11it/s] Loading 0: 92%|█████████▏| 267/291 [00:07<00:00, 91.82it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 108.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: quantized model in 22.738s
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Processed model Kaoeiri/Keiana-L3-Test6.2-8B-18 in 86.695s
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: creating bucket guanaco-mkml-models
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/kaoeiri-keiana-l3-test6-7421-v1
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/kaoeiri-keiana-l3-test6-7421-v1/config.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/kaoeiri-keiana-l3-test6-7421-v1/special_tokens_map.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/kaoeiri-keiana-l3-test6-7421-v1/tokenizer_config.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/kaoeiri-keiana-l3-test6-7421-v1/tokenizer.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/kaoeiri-keiana-l3-test6-7421-v1/flywheel_model.0.safetensors
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
kaoeiri-keiana-l3-test6-7421-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-keiana-l3-test6-7421-v1-mkmlizer: warnings.warn(
kaoeiri-keiana-l3-test6-7421-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-keiana-l3-test6-7421-v1-mkmlizer: warnings.warn(
kaoeiri-keiana-l3-test6-7421-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-keiana-l3-test6-7421-v1-mkmlizer: warnings.warn(
kaoeiri-keiana-l3-test6-7421-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-keiana-l3-test6-7421-v1-mkmlizer: return self.fget.__get__(instance, owner)()
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Saving duration: 0.406s
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.775s
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: creating bucket guanaco-reward-models
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/special_tokens_map.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/config.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/merges.txt
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/tokenizer_config.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/vocab.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/tokenizer.json
kaoeiri-keiana-l3-test6-7421-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/kaoeiri-keiana-l3-test6-7421-v1_reward/reward.tensors
Job kaoeiri-keiana-l3-test6-7421-v1-mkmlizer completed after 114.55s with status: succeeded
Stopping job with name kaoeiri-keiana-l3-test6-7421-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service kaoeiri-keiana-l3-test6-7421-v1
Waiting for inference service kaoeiri-keiana-l3-test6-7421-v1 to be ready
Inference service kaoeiri-keiana-l3-test6-7421-v1 ready after 40.23130750656128s
Pipeline stage ISVCDeployer completed in 47.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1914360523223877s
Received healthy response to inference request in 1.3262598514556885s
Received healthy response to inference request in 1.3162446022033691s
Received healthy response to inference request in 1.305546760559082s
Received healthy response to inference request in 1.3140807151794434s
5 requests
0 failed requests
5th percentile: 1.3072535514831543
10th percentile: 1.3089603424072265
20th percentile: 1.3123739242553711
30th percentile: 1.3145134925842286
40th percentile: 1.3153790473937987
50th percentile: 1.3162446022033691
60th percentile: 1.3202507019042968
70th percentile: 1.3242568016052245
80th percentile: 1.4992950916290284
90th percentile: 1.845365571975708
95th percentile: 2.0184008121490478
99th percentile: 2.1568290042877196
mean time: 1.4907135963439941
Pipeline stage StressChecker completed in 8.33s
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-keiana-l3-test6-_7421_v1 status is now deployed due to DeploymentManager action
kaoeiri-keiana-l3-test6-_7421_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics