submission_id: cgato-blipblop-l3-8b-v0-2-1_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/BlipBlop-L3-8b-v0.2.1
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: 2024-06-12T10:20:32+00:00
model_name: cgato-blipblop-l3-8b-v0-2-1_v1
model_eval_status: success
model_group: cgato/BlipBlop-L3-8b-v0.
num_battles: 31461
num_wins: 17143
celo_rating: 1198.71
propriety_score: 0.6977815966255273
propriety_total_count: 12802.0
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-blipblop-l3-8b-v0-2-1_v1
ineligible_reason: None
language_model: cgato/BlipBlop-L3-8b-v0.2.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.5448968564254156
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer
Waiting for job on cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer to finish
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ _____ __ __ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ /___/ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ https://mk1.ai ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ belonging to: ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-blipblop-l3-8b-v0-2-1-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.
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Downloaded to shared memory in 44.279s
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 124.78it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 145.75it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 152.78it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 153.71it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 149.09it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 71.97it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 88.98it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 104.38it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 118.70it/s] Loading 0: 56%|█████▌ | 163/291 [00:01<00:00, 128.36it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 134.25it/s] Loading 0: 67%|██████▋ | 196/291 [00:01<00:01, 78.63it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 91.33it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 106.34it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 119.72it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 130.95it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 142.36it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: quantized model in 18.593s
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Processed model cgato/BlipBlop-L3-8b-v0.2.1 in 63.868s
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-blipblop-l3-8b-v0-2-1-v1
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-v0-2-1-v1/config.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-v0-2-1-v1/special_tokens_map.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-v0-2-1-v1/tokenizer_config.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-v0-2-1-v1/tokenizer.json
cgato-blipblop-l3-8b-v0-2-1-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.
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: warnings.warn(
cgato-blipblop-l3-8b-v0-2-1-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()
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Saving duration: 0.293s
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.016s
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/config.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/special_tokens_map.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/tokenizer_config.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/merges.txt
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/vocab.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/tokenizer.json
cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-blipblop-l3-8b-v0-2-1-v1_reward/reward.tensors
Job cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer completed after 107.96s with status: succeeded
Stopping job with name cgato-blipblop-l3-8b-v0-2-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 108.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-blipblop-l3-8b-v0-2-1-v1
Waiting for inference service cgato-blipblop-l3-8b-v0-2-1-v1 to be ready
Inference service cgato-blipblop-l3-8b-v0-2-1-v1 ready after 111.36646223068237s
Pipeline stage ISVCDeployer completed in 116.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.191744327545166s
Received healthy response to inference request in 1.277400255203247s
Received healthy response to inference request in 1.2811472415924072s
Received healthy response to inference request in 1.2946527004241943s
Received healthy response to inference request in 1.2736248970031738s
5 requests
0 failed requests
5th percentile: 1.2743799686431885
10th percentile: 1.2751350402832031
20th percentile: 1.2766451835632324
30th percentile: 1.2781496524810791
40th percentile: 1.279648447036743
50th percentile: 1.2811472415924072
60th percentile: 1.2865494251251222
70th percentile: 1.2919516086578369
80th percentile: 1.474071025848389
90th percentile: 1.8329076766967773
95th percentile: 2.0123260021209717
99th percentile: 2.155860662460327
mean time: 1.4637138843536377
Pipeline stage StressChecker completed in 7.94s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-blipblop-l3-8b-v0-2-1_v1 status is now deployed due to DeploymentManager action
cgato-blipblop-l3-8b-v0-2-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics