submission_id: alsebay-smaid-v0-3_v1
developer_uid: Alsebay
status: inactive
model_repo: Alsebay/SMaid-v0.3
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: 2024-06-22T10:28:29+00:00
model_name: alsebay-smaid-v0-3_v1
model_group: Alsebay/SMaid-v0.3
num_battles: 22853
num_wins: 12422
celo_rating: 1196.62
propriety_score: 0.7232836639546576
propriety_total_count: 10939.0
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-v0-3_v1
ineligible_reason: None
language_model: Alsebay/SMaid-v0.3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.5435610204349538
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-3-v1-mkmlizer
Waiting for job on alsebay-smaid-v0-3-v1-mkmlizer to finish
alsebay-smaid-v0-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-3-v1-mkmlizer: ║ _____ __ __ ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ /___/ ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ Version: 0.8.14 ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ https://mk1.ai ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ belonging to: ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ Chai Research Corp. ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alsebay-smaid-v0-3-v1-mkmlizer: ║ ║
alsebay-smaid-v0-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-3-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-v0-3-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
alsebay-smaid-v0-3-v1-mkmlizer: Downloaded to shared memory in 44.378s
alsebay-smaid-v0-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
alsebay-smaid-v0-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:59, 2.28s/it] Loading 0: 6%|▌ | 17/291 [00:04<00:55, 4.97it/s] Loading 0: 9%|▉ | 26/291 [00:04<00:32, 8.17it/s] Loading 0: 14%|█▍ | 42/291 [00:04<00:15, 16.30it/s] Loading 0: 20%|██ | 59/291 [00:05<00:08, 27.16it/s] Loading 0: 25%|██▍ | 72/291 [00:05<00:06, 33.39it/s] Loading 0: 30%|██▉ | 87/291 [00:05<00:04, 45.83it/s] Loading 0: 35%|███▌ | 103/291 [00:05<00:03, 52.97it/s] Loading 0: 42%|████▏ | 121/291 [00:05<00:02, 70.41it/s] Loading 0: 48%|████▊ | 139/291 [00:05<00:01, 87.44it/s] Loading 0: 53%|█████▎ | 153/291 [00:06<00:01, 77.62it/s] Loading 0: 58%|█████▊ | 169/291 [00:06<00:01, 92.16it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 85.47it/s] Loading 0: 69%|██████▊ | 200/291 [00:06<00:00, 99.61it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:00, 110.22it/s] Loading 0: 79%|███████▊ | 229/291 [00:06<00:00, 94.56it/s] Loading 0: 85%|████████▍ | 247/291 [00:06<00:00, 110.80it/s] Loading 0: 91%|█████████ | 265/291 [00:07<00:00, 94.66it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 108.47it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alsebay-smaid-v0-3-v1-mkmlizer: Processed model Alsebay/SMaid-v0.3 in 70.344s
alsebay-smaid-v0-3-v1-mkmlizer: creating bucket guanaco-mkml-models
alsebay-smaid-v0-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alsebay-smaid-v0-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alsebay-smaid-v0-3-v1
alsebay-smaid-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v1/special_tokens_map.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v1/tokenizer_config.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v1/config.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alsebay-smaid-v0-3-v1/tokenizer.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alsebay-smaid-v0-3-v1/flywheel_model.0.safetensors
alsebay-smaid-v0-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alsebay-smaid-v0-3-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.
alsebay-smaid-v0-3-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-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-v0-3-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-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-v0-3-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-3-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-v0-3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
alsebay-smaid-v0-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-3-v1-mkmlizer: Saving duration: 0.385s
alsebay-smaid-v0-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.203s
alsebay-smaid-v0-3-v1-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/config.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/special_tokens_map.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/tokenizer_config.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/merges.txt
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/vocab.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/tokenizer.json
alsebay-smaid-v0-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alsebay-smaid-v0-3-v1_reward/reward.tensors
Job alsebay-smaid-v0-3-v1-mkmlizer completed after 93.34s with status: succeeded
Stopping job with name alsebay-smaid-v0-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 93.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-3-v1
Waiting for inference service alsebay-smaid-v0-3-v1 to be ready
Inference service alsebay-smaid-v0-3-v1 ready after 40.19410181045532s
Pipeline stage ISVCDeployer completed in 45.93s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.949500322341919s
Received healthy response to inference request in 1.1680850982666016s
Received healthy response to inference request in 1.1150829792022705s
Received healthy response to inference request in 1.187307357788086s
Received healthy response to inference request in 1.0986559391021729s
5 requests
0 failed requests
5th percentile: 1.1019413471221924
10th percentile: 1.105226755142212
20th percentile: 1.111797571182251
30th percentile: 1.1256834030151368
40th percentile: 1.1468842506408692
50th percentile: 1.1680850982666016
60th percentile: 1.1757740020751952
70th percentile: 1.183462905883789
80th percentile: 1.3397459506988527
90th percentile: 1.6446231365203858
95th percentile: 1.7970617294311522
99th percentile: 1.9190126037597657
mean time: 1.3037263393402099
Pipeline stage StressChecker completed in 7.26s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
alsebay-smaid-v0-3_v1 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-3_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics