submission_id: cycy233-l3-base-v1-e2-5_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base-v1-e2.5
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': True}
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': True}
timestamp: 2024-06-21T02:34:05+00:00
model_name: base
model_group: cycy233/L3-base-v1-e2.5
num_battles: 20032
num_wins: 10137
celo_rating: 1197.39
propriety_score: 0.6970445886108537
propriety_total_count: 9711.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
ineligible_reason: None
language_model: cycy233/L3-base-v1-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-20
win_ratio: 0.5060403354632588
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v1-e2-5-v2-mkmlizer
Waiting for job on cycy233-l3-base-v1-e2-5-v2-mkmlizer to finish
Stopping job with name cycy233-l3-base-v1-e2-5-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-base-v1-e2-5-v2-mkmlizer
Waiting for job on cycy233-l3-base-v1-e2-5-v2-mkmlizer to finish
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ /___/ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ║ ║
cycy233-l3-base-v1-e2-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v1-e2-5-v2-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-l3-base-v1-e2-5-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Downloaded to shared memory in 27.079s
cycy233-l3-base-v1-e2-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 73.96it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 86.18it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 125.25it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v1-e2-5-v2-mkmlizer: quantized model in 19.606s
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Processed model cycy233/L3-base-v1-e2.5 in 47.796s
cycy233-l3-base-v1-e2-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v1-e2-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v1-e2-5-v2
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e2-5-v2/config.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e2-5-v2/special_tokens_map.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e2-5-v2/tokenizer_config.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v1-e2-5-v2/tokenizer.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v1-e2-5-v2-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-l3-base-v1-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v1-e2-5-v2-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-l3-base-v1-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v1-e2-5-v2-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-l3-base-v1-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v1-e2-5-v2-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-l3-base-v1-e2-5-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Saving duration: 0.291s
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.375s
cycy233-l3-base-v1-e2-5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v1-e2-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v1-e2-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v1-e2-5-v2_reward
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v1-e2-5-v2_reward/config.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v1-e2-5-v2_reward/tokenizer_config.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v1-e2-5-v2_reward/special_tokens_map.json
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v1-e2-5-v2_reward/merges.txt
cycy233-l3-base-v1-e2-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v1-e2-5-v2_reward/reward.tensors
Job cycy233-l3-base-v1-e2-5-v2-mkmlizer completed after 84.73s with status: succeeded
Stopping job with name cycy233-l3-base-v1-e2-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v1-e2-5-v2
Waiting for inference service cycy233-l3-base-v1-e2-5-v2 to be ready
Inference service cycy233-l3-base-v1-e2-5-v2 ready after 40.249449253082275s
Pipeline stage ISVCDeployer completed in 45.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1177818775177s
Received healthy response to inference request in 1.2165861129760742s
Received healthy response to inference request in 1.236490249633789s
Received healthy response to inference request in 3.3334362506866455s
Received healthy response to inference request in 1.2248225212097168s
5 requests
0 failed requests
5th percentile: 1.2182333946228028
10th percentile: 1.2198806762695313
20th percentile: 1.2231752395629882
30th percentile: 1.2271560668945312
40th percentile: 1.2318231582641601
50th percentile: 1.236490249633789
60th percentile: 1.5890069007873535
70th percentile: 1.9415235519409177
80th percentile: 2.3609127521514894
90th percentile: 2.8471745014190675
95th percentile: 3.0903053760528563
99th percentile: 3.2848100757598875
mean time: 1.8258234024047852
Pipeline stage StressChecker completed in 9.79s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-l3-base-v1-e2-5_v2 status is now deployed due to DeploymentManager action
cycy233-l3-base-v1-e2-5_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics