submission_id: cgato-blopblip-l3-8b-v0-1-1_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/BlopBlip-L3-8b-v0.1.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], '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: 2024-06-15T02:45:53+00:00
model_name: cgato-blopblip-l3-8b-v0-1-1_v2
model_eval_status: success
model_group: cgato/BlopBlip-L3-8b-v0.
num_battles: 21953
num_wins: 10896
celo_rating: 1189.03
propriety_score: 0.6702149437052201
propriety_total_count: 9770.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-blopblip-l3-8b-v0-1-1_v2
ineligible_reason: None
language_model: cgato/BlopBlip-L3-8b-v0.1.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-14
win_ratio: 0.4963330752061222
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer
Waiting for job on cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer to finish
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ _____ __ __ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ /___/ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ https://mk1.ai ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ belonging to: ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ║ ║
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-blopblip-l3-8b-v0-1-1-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.
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Downloaded to shared memory in 17.586s
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 137.55it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 154.89it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 158.69it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 162.50it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 83.52it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 100.91it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 116.27it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 128.15it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 136.31it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 146.52it/s] Loading 0: 66%|██████▌ | 192/291 [00:01<00:01, 90.58it/s] Loading 0: 72%|███████▏ | 210/291 [00:01<00:00, 105.30it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 119.47it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 131.17it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 140.71it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 144.36it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: quantized model in 22.687s
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Processed model cgato/BlopBlip-L3-8b-v0.1.1 in 42.841s
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v2
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v2/config.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v2/tokenizer_config.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v2/special_tokens_map.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v2/tokenizer.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v2/flywheel_model.0.safetensors
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-blopblip-l3-8b-v0-1-1-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.
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: warnings.warn(
cgato-blopblip-l3-8b-v0-1-1-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.
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: warnings.warn(
cgato-blopblip-l3-8b-v0-1-1-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.
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: warnings.warn(
cgato-blopblip-l3-8b-v0-1-1-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()
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Saving duration: 0.398s
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.832s
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/special_tokens_map.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/vocab.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/config.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/tokenizer.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/tokenizer_config.json
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/merges.txt
cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v2_reward/reward.tensors
Job cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer completed after 73.71s with status: succeeded
Stopping job with name cgato-blopblip-l3-8b-v0-1-1-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-blopblip-l3-8b-v0-1-1-v2
Waiting for inference service cgato-blopblip-l3-8b-v0-1-1-v2 to be ready
Inference service cgato-blopblip-l3-8b-v0-1-1-v2 ready after 50.35381841659546s
Pipeline stage ISVCDeployer completed in 57.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.120793104171753s
Received healthy response to inference request in 1.2190032005310059s
Received healthy response to inference request in 1.2344951629638672s
Received healthy response to inference request in 1.2355594635009766s
Received healthy response to inference request in 1.2442591190338135s
5 requests
0 failed requests
5th percentile: 1.222101593017578
10th percentile: 1.2251999855041504
20th percentile: 1.231396770477295
30th percentile: 1.234708023071289
40th percentile: 1.235133743286133
50th percentile: 1.2355594635009766
60th percentile: 1.2390393257141112
70th percentile: 1.2425191879272461
80th percentile: 1.4195659160614016
90th percentile: 1.7701795101165771
95th percentile: 1.9454863071441648
99th percentile: 2.0857317447662354
mean time: 1.4108220100402833
Pipeline stage StressChecker completed in 7.61s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-blopblip-l3-8b-v0-1-1_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-blopblip-l3-8b-v0-1-1_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics