submission_id: alsebay-smaid-v0-2_v1
developer_uid: Alsebay
status: inactive
model_repo: Alsebay/SMaid-v0.2
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: 2024-06-22T09:56:40+00:00
model_name: alsebay-smaid-v0-2_v1
model_group: Alsebay/SMaid-v0.2
num_battles: 31906
num_wins: 15398
celo_rating: 1163.0
propriety_score: 0.7216296787015568
propriety_total_count: 15095.0
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-v0-2_v1
ineligible_reason: None
language_model: Alsebay/SMaid-v0.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.48260515263586784
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-2-v1-mkmlizer
Waiting for job on alsebay-smaid-v0-2-v1-mkmlizer to finish
alsebay-smaid-v0-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-2-v1-mkmlizer: ║ _____ __ __ ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ /___/ ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ Version: 0.8.14 ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ https://mk1.ai ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ belonging to: ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ Chai Research Corp. ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alsebay-smaid-v0-2-v1-mkmlizer: ║ ║
alsebay-smaid-v0-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-2-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-v0-2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
alsebay-smaid-v0-2-v1-mkmlizer: Downloaded to shared memory in 38.521s
alsebay-smaid-v0-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
alsebay-smaid-v0-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:12, 2.33s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:04, 4.27it/s] Loading 0: 8%|▊ | 22/291 [00:04<00:40, 6.72it/s] Loading 0: 12%|█▏ | 35/291 [00:05<00:19, 13.28it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:10, 22.20it/s] Loading 0: 21%|██ | 60/291 [00:05<00:08, 27.42it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:04, 43.14it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 60.33it/s] Loading 0: 37%|███▋ | 109/291 [00:05<00:02, 61.93it/s] Loading 0: 43%|████▎ | 126/291 [00:05<00:02, 79.10it/s] Loading 0: 48%|████▊ | 141/291 [00:06<00:02, 73.13it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 90.54it/s] Loading 0: 61%|██████ | 177/291 [00:06<00:01, 106.82it/s] Loading 0: 66%|██████▌ | 191/291 [00:06<00:01, 93.42it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:00, 102.78it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 90.22it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 106.47it/s] Loading 0: 89%|████████▊ | 258/291 [00:07<00:00, 120.81it/s] Loading 0: 93%|█████████▎| 272/291 [00:07<00:00, 102.68it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 116.55it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alsebay-smaid-v0-2-v1-mkmlizer: quantized model in 23.224s
alsebay-smaid-v0-2-v1-mkmlizer: Processed model Alsebay/SMaid-v0.2 in 64.227s
alsebay-smaid-v0-2-v1-mkmlizer: creating bucket guanaco-mkml-models
alsebay-smaid-v0-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alsebay-smaid-v0-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alsebay-smaid-v0-2-v1
alsebay-smaid-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alsebay-smaid-v0-2-v1/config.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alsebay-smaid-v0-2-v1/special_tokens_map.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alsebay-smaid-v0-2-v1/tokenizer_config.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alsebay-smaid-v0-2-v1/tokenizer.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alsebay-smaid-v0-2-v1/flywheel_model.0.safetensors
alsebay-smaid-v0-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alsebay-smaid-v0-2-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-v0-2-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-2-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-v0-2-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-2-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-v0-2-v1-mkmlizer: warnings.warn(
alsebay-smaid-v0-2-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-v0-2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
alsebay-smaid-v0-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-2-v1-mkmlizer: Saving duration: 0.387s
alsebay-smaid-v0-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.998s
alsebay-smaid-v0-2-v1-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/config.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/special_tokens_map.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/tokenizer_config.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/merges.txt
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/vocab.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/tokenizer.json
alsebay-smaid-v0-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alsebay-smaid-v0-2-v1_reward/reward.tensors
Job alsebay-smaid-v0-2-v1-mkmlizer completed after 94.38s with status: succeeded
Stopping job with name alsebay-smaid-v0-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.17s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-2-v1
Waiting for inference service alsebay-smaid-v0-2-v1 to be ready
Inference service alsebay-smaid-v0-2-v1 ready after 40.19726252555847s
Pipeline stage ISVCDeployer completed in 45.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1221790313720703s
Received healthy response to inference request in 1.134660243988037s
Received healthy response to inference request in 1.13559889793396s
Received healthy response to inference request in 1.1146929264068604s
Received healthy response to inference request in 1.1613683700561523s
5 requests
0 failed requests
5th percentile: 1.1186863899230957
10th percentile: 1.122679853439331
20th percentile: 1.1306667804718018
30th percentile: 1.1348479747772218
40th percentile: 1.1352234363555909
50th percentile: 1.13559889793396
60th percentile: 1.145906686782837
70th percentile: 1.1562144756317139
80th percentile: 1.353530502319336
90th percentile: 1.7378547668457032
95th percentile: 1.9300168991088866
99th percentile: 2.0837466049194338
mean time: 1.333699893951416
Pipeline stage StressChecker completed in 8.07s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.06s
alsebay-smaid-v0-2_v1 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-2_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics