submission_id: cycy233-super-cool_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/super-cool
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': 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: 2024-06-21T09:57:30+00:00
model_name: cycy233-super-cool_v1
model_group: cycy233/super-cool
num_battles: 21091
num_wins: 10997
celo_rating: 1203.02
propriety_score: 0.7050572896088503
propriety_total_count: 10124.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-super-cool_v1
ineligible_reason: None
language_model: cycy233/super-cool
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-21
win_ratio: 0.5214072353136409
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-super-cool-v1-mkmlizer
Waiting for job on cycy233-super-cool-v1-mkmlizer to finish
cycy233-super-cool-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-super-cool-v1-mkmlizer: ║ _____ __ __ ║
cycy233-super-cool-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-super-cool-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-super-cool-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-super-cool-v1-mkmlizer: ║ /___/ ║
cycy233-super-cool-v1-mkmlizer: ║ ║
cycy233-super-cool-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-super-cool-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-super-cool-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-super-cool-v1-mkmlizer: ║ ║
cycy233-super-cool-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-super-cool-v1-mkmlizer: ║ belonging to: ║
cycy233-super-cool-v1-mkmlizer: ║ ║
cycy233-super-cool-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-super-cool-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-super-cool-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-super-cool-v1-mkmlizer: ║ ║
cycy233-super-cool-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-super-cool-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.
cycy233-super-cool-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-super-cool-v1-mkmlizer: Downloaded to shared memory in 45.091s
cycy233-super-cool-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-super-cool-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-super-cool-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:00<00:18, 16.05it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 63.35it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 75.38it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 110.17it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-super-cool-v1-mkmlizer: quantized model in 24.739s
cycy233-super-cool-v1-mkmlizer: Processed model cycy233/super-cool in 72.360s
cycy233-super-cool-v1-mkmlizer: creating bucket guanaco-mkml-models
Retrying (%r) after connection broken by '%r': %s
cycy233-super-cool-v1-mkmlizer: WARNING: Retrying failed request: /?location ([Errno 110] Connection timed out)
cycy233-super-cool-v1-mkmlizer: WARNING: Waiting 3 sec...
cycy233-super-cool-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-super-cool-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-super-cool-v1
cycy233-super-cool-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-super-cool-v1/config.json
cycy233-super-cool-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-super-cool-v1/special_tokens_map.json
cycy233-super-cool-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-super-cool-v1/tokenizer_config.json
cycy233-super-cool-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-super-cool-v1/tokenizer.json
cycy233-super-cool-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-super-cool-v1/flywheel_model.0.safetensors
cycy233-super-cool-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-super-cool-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.
cycy233-super-cool-v1-mkmlizer: warnings.warn(
cycy233-super-cool-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.
cycy233-super-cool-v1-mkmlizer: warnings.warn(
cycy233-super-cool-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.
cycy233-super-cool-v1-mkmlizer: warnings.warn(
cycy233-super-cool-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()
cycy233-super-cool-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-super-cool-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-super-cool-v1-mkmlizer: Saving duration: 0.405s
cycy233-super-cool-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.678s
cycy233-super-cool-v1-mkmlizer: creating bucket guanaco-reward-models
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cycy233-super-cool-v1-mkmlizer: WARNING: Retrying failed request: /?location ([Errno 110] Connection timed out)
cycy233-super-cool-v1-mkmlizer: WARNING: Waiting 3 sec...
cycy233-super-cool-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-super-cool-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-super-cool-v1_reward
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-super-cool-v1_reward/config.json
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-super-cool-v1_reward/tokenizer_config.json
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-super-cool-v1_reward/special_tokens_map.json
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-super-cool-v1_reward/merges.txt
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-super-cool-v1_reward/vocab.json
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-super-cool-v1_reward/tokenizer.json
cycy233-super-cool-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-super-cool-v1_reward/reward.tensors
Job cycy233-super-cool-v1-mkmlizer completed after 380.24s with status: succeeded
Stopping job with name cycy233-super-cool-v1-mkmlizer
Pipeline stage MKMLizer completed in 380.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-super-cool-v1
Waiting for inference service cycy233-super-cool-v1 to be ready
Inference service cycy233-super-cool-v1 ready after 120.5434319972992s
Pipeline stage ISVCDeployer completed in 126.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1738815307617188s
Received healthy response to inference request in 1.262789011001587s
Received healthy response to inference request in 1.2546250820159912s
Received healthy response to inference request in 1.5142614841461182s
Received healthy response to inference request in 1.2633702754974365s
5 requests
0 failed requests
5th percentile: 1.2562578678131104
10th percentile: 1.2578906536102294
20th percentile: 1.2611562252044677
30th percentile: 1.2629052639007567
40th percentile: 1.2631377696990966
50th percentile: 1.2633702754974365
60th percentile: 1.363726758956909
70th percentile: 1.4640832424163819
80th percentile: 1.6461854934692384
90th percentile: 1.9100335121154786
95th percentile: 2.0419575214385985
99th percentile: 2.1474967288970945
mean time: 1.4937854766845704
Pipeline stage StressChecker completed in 8.26s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-super-cool_v1 status is now deployed due to DeploymentManager action
cycy233-super-cool_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics