submission_id: bbchicago-test-l3-8b-instruct_v3
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/test-L3-8B-instruct
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: 2024-07-03T05:36:01+00:00
model_name: bbchicago-test-l3-8b-instruct_v3
model_group: BBChicago/test-L3-8B-ins
num_battles: 20842
num_wins: 10339
celo_rating: 1173.75
propriety_score: 0.7245065789473685
propriety_total_count: 9728.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: bbchicago-test-l3-8b-instruct_v3
ineligible_reason: None
language_model: BBChicago/test-L3-8B-instruct
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.4960656366951348
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-test-l3-8b-instruct-v3-mkmlizer
Waiting for job on bbchicago-test-l3-8b-instruct-v3-mkmlizer to finish
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ _____ __ __ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ /___/ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ https://mk1.ai ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ belonging to: ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ Chai Research Corp. ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ║ ║
bbchicago-test-l3-8b-instruct-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Downloaded to shared memory in 50.996s
bbchicago-test-l3-8b-instruct-v3-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 122.26it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 143.13it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 149.72it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 147.77it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:01, 142.76it/s] Loading 0: 32%|███▏ | 94/291 [00:00<00:02, 73.98it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:01, 91.34it/s] Loading 0: 43%|████▎ | 126/291 [00:01<00:01, 103.08it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 109.06it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 122.37it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 130.90it/s] Loading 0: 65%|██████▍ | 188/291 [00:01<00:01, 81.79it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 90.81it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 105.84it/s] Loading 0: 80%|████████ | 234/291 [00:02<00:00, 115.07it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 118.89it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 130.85it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 137.56it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-l3-8b-instruct-v3-mkmlizer: quantized model in 23.638s
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Processed model BBChicago/test-L3-8B-instruct in 74.634s
bbchicago-test-l3-8b-instruct-v3-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-l3-8b-instruct-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v3
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v3/special_tokens_map.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v3/config.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v3/tokenizer_config.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v3/tokenizer.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-l3-8b-instruct-v3/flywheel_model.0.safetensors
bbchicago-test-l3-8b-instruct-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-l3-8b-instruct-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-l3-8b-instruct-v3-mkmlizer: warnings.warn(
bbchicago-test-l3-8b-instruct-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
bbchicago-test-l3-8b-instruct-v3-mkmlizer: warnings.warn(
bbchicago-test-l3-8b-instruct-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-l3-8b-instruct-v3-mkmlizer: warnings.warn(
bbchicago-test-l3-8b-instruct-v3-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.
bbchicago-test-l3-8b-instruct-v3-mkmlizer: warnings.warn(
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Saving duration: 0.396s
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.259s
bbchicago-test-l3-8b-instruct-v3-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-l3-8b-instruct-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-l3-8b-instruct-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/config.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/special_tokens_map.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/tokenizer_config.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/merges.txt
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/vocab.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/tokenizer.json
bbchicago-test-l3-8b-instruct-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-l3-8b-instruct-v3_reward/reward.tensors
Job bbchicago-test-l3-8b-instruct-v3-mkmlizer completed after 104.42s with status: succeeded
Stopping job with name bbchicago-test-l3-8b-instruct-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-l3-8b-instruct-v3
Waiting for inference service bbchicago-test-l3-8b-instruct-v3 to be ready
Connection pool is full, discarding connection: %s
Inference service bbchicago-test-l3-8b-instruct-v3 ready after 40.178800106048584s
Pipeline stage ISVCDeployer completed in 47.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.107856035232544s
Received healthy response to inference request in 1.236933946609497s
Received healthy response to inference request in 1.253309726715088s
Received healthy response to inference request in 1.2306005954742432s
Received healthy response to inference request in 1.2326574325561523s
5 requests
0 failed requests
5th percentile: 1.231011962890625
10th percentile: 1.2314233303070068
20th percentile: 1.2322460651397704
30th percentile: 1.2335127353668214
40th percentile: 1.2352233409881592
50th percentile: 1.236933946609497
60th percentile: 1.2434842586517334
70th percentile: 1.2500345706939697
80th percentile: 1.4242189884185792
90th percentile: 1.7660375118255616
95th percentile: 1.9369467735290526
99th percentile: 2.0736741828918457
mean time: 1.412271547317505
Pipeline stage StressChecker completed in 8.03s
bbchicago-test-l3-8b-instruct_v3 status is now deployed due to DeploymentManager action
bbchicago-test-l3-8b-instruct_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics