submission_id: alsebay-smaid-v0-1_v1
developer_uid: Alsebay
status: inactive
model_repo: Alsebay/SMaid-v0.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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: {'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: 2024-06-22T09:06:39+00:00
model_name: alsebay-smaid-v0-1_v1
model_group: Alsebay/SMaid-v0.1
num_battles: 30230
num_wins: 14641
celo_rating: 1163.73
propriety_score: 0.7199915469146239
propriety_total_count: 14196.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: alsebay-smaid-v0-1_v1
ineligible_reason: None
language_model: Alsebay/SMaid-v0.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.48432021171022166
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-1-v1-mkmlizer
Waiting for job on alsebay-smaid-v0-1-v1-mkmlizer to finish
alsebay-smaid-v0-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-1-v1-mkmlizer: ║ _____ __ __ ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ /___/ ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ Version: 0.8.14 ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ https://mk1.ai ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ belonging to: ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ Chai Research Corp. ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alsebay-smaid-v0-1-v1-mkmlizer: ║ ║
alsebay-smaid-v0-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-1-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.
alsebay-smaid-v0-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
alsebay-smaid-v0-1-v1-mkmlizer: Downloaded to shared memory in 42.502s
alsebay-smaid-v0-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
alsebay-smaid-v0-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:05, 2.30s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.32it/s] Loading 0: 8%|▊ | 22/291 [00:04<00:39, 6.78it/s] Loading 0: 14%|█▎ | 40/291 [00:05<00:15, 15.96it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:08, 27.38it/s] Loading 0: 24%|██▍ | 71/291 [00:05<00:06, 33.27it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 46.28it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 53.45it/s] Loading 0: 42%|████▏ | 121/291 [00:05<00:02, 70.31it/s] Loading 0: 48%|████▊ | 139/291 [00:05<00:01, 87.33it/s] Loading 0: 53%|█████▎ | 153/291 [00:06<00:01, 79.62it/s] Loading 0: 58%|█████▊ | 168/291 [00:06<00:01, 92.05it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 83.36it/s] Loading 0: 68%|██████▊ | 197/291 [00:06<00:01, 92.07it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 103.11it/s] Loading 0: 78%|███████▊ | 226/291 [00:06<00:00, 85.74it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 95.29it/s] Loading 0: 89%|████████▊ | 258/291 [00:07<00:00, 111.14it/s] Loading 0: 93%|█████████▎| 271/291 [00:07<00:00, 92.48it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 102.35it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alsebay-smaid-v0-1-v1-mkmlizer: quantized model in 23.802s
alsebay-smaid-v0-1-v1-mkmlizer: Processed model Alsebay/SMaid-v0.1 in 68.848s
alsebay-smaid-v0-1-v1-mkmlizer: creating bucket guanaco-mkml-models
alsebay-smaid-v0-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alsebay-smaid-v0-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alsebay-smaid-v0-1-v1
alsebay-smaid-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v1/special_tokens_map.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v1/config.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v1/tokenizer_config.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alsebay-smaid-v0-1-v1/tokenizer.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alsebay-smaid-v0-1-v1/flywheel_model.0.safetensors
alsebay-smaid-v0-1-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.
alsebay-smaid-v0-1-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-1-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.
alsebay-smaid-v0-1-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-1-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()
alsebay-smaid-v0-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
alsebay-smaid-v0-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-1-v1-mkmlizer: Saving duration: 0.403s
alsebay-smaid-v0-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.883s
alsebay-smaid-v0-1-v1-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/config.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/tokenizer_config.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/special_tokens_map.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/vocab.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/merges.txt
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/tokenizer.json
alsebay-smaid-v0-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alsebay-smaid-v0-1-v1_reward/reward.tensors
Job alsebay-smaid-v0-1-v1-mkmlizer completed after 93.98s with status: succeeded
Stopping job with name alsebay-smaid-v0-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-1-v1
Waiting for inference service alsebay-smaid-v0-1-v1 to be ready
Inference service alsebay-smaid-v0-1-v1 ready after 40.204564332962036s
Pipeline stage ISVCDeployer completed in 45.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.05430269241333s
Received healthy response to inference request in 1.1319918632507324s
Received healthy response to inference request in 3.699174404144287s
Received healthy response to inference request in 1.0945219993591309s
Received healthy response to inference request in 1.1084904670715332s
5 requests
0 failed requests
5th percentile: 1.0973156929016112
10th percentile: 1.1001093864440918
20th percentile: 1.1056967735290528
30th percentile: 1.1131907463073731
40th percentile: 1.1225913047790528
50th percentile: 1.1319918632507324
60th percentile: 1.5009161949157714
70th percentile: 1.8698405265808105
80th percentile: 2.383277034759522
90th percentile: 3.0412257194519046
95th percentile: 3.370200061798095
99th percentile: 3.633379535675049
mean time: 1.8176962852478027
Pipeline stage StressChecker completed in 9.79s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
alsebay-smaid-v0-1_v1 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics