submission_id: bbchicago-l3-8b-fusion-v0-0-0_v2
developer_uid: Bbbrun0
status: inactive
model_repo: BBChicago/L3-8B-fusion-v0.0.0
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: 2024-06-03T10:35:13+00:00
model_name: bbchicago-l3-8b-fusion-v0-0-0_v2
model_eval_status: success
model_group: BBChicago/L3-8B-fusion-v
num_battles: 52194
num_wins: 27637
celo_rating: 1206.82
safety_score: 0.91
propriety_score: 0.6600517687661778
propriety_total_count: 1159.0
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-l3-8b-fusion-v0-0-0_v2
ineligible_reason: propriety_total_count < 5000
language_model: BBChicago/L3-8B-fusion-v0.0.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-03
win_ratio: 0.5295053071234241
Resubmit model
Running pipeline stage MKMLizer
Starting job with name bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer
Waiting for job on bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer to finish
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ _____ __ __ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ /___/ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ https://mk1.ai ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ belonging to: ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ Chai Research Corp. ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ║ ║
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-l3-8b-fusion-v0-0-0-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.
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Downloaded to shared memory in 17.145s
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:48, 2.24s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.44it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.82it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.24it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.30it/s] Loading 0: 27%|██▋ | 80/291 [00:05<00:05, 35.55it/s] Loading 0: 33%|███▎ | 95/291 [00:05<00:04, 47.30it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 63.80it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 80.89it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 97.11it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.68it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 89.94it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 105.36it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 119.58it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 131.48it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 140.84it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 93.03it/s] Loading 0: 98%|█████████▊| 286/291 [00:07<00:00, 99.79it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: quantized model in 22.866s
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Processed model BBChicago/L3-8B-fusion-v0.0.0 in 42.575s
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-v0-0-0-v2
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-v0-0-0-v2/config.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-v0-0-0-v2/tokenizer_config.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-v0-0-0-v2/special_tokens_map.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-v0-0-0-v2/tokenizer.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-l3-8b-fusion-v0-0-0-v2/flywheel_model.0.safetensors
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-l3-8b-fusion-v0-0-0-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.
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: warnings.warn(
bbchicago-l3-8b-fusion-v0-0-0-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.
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: warnings.warn(
bbchicago-l3-8b-fusion-v0-0-0-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.
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: warnings.warn(
bbchicago-l3-8b-fusion-v0-0-0-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()
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Saving duration: 0.407s
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.066s
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: creating bucket guanaco-reward-models
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/config.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/special_tokens_map.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/tokenizer_config.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/merges.txt
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/vocab.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/tokenizer.json
bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-l3-8b-fusion-v0-0-0-v2_reward/reward.tensors
Job bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer completed after 72.81s with status: succeeded
Stopping job with name bbchicago-l3-8b-fusion-v0-0-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.65s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-l3-8b-fusion-v0-0-0-v2
Waiting for inference service bbchicago-l3-8b-fusion-v0-0-0-v2 to be ready
Inference service bbchicago-l3-8b-fusion-v0-0-0-v2 ready after 30.173794984817505s
Pipeline stage ISVCDeployer completed in 37.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.154491424560547s
Received healthy response to inference request in 1.2475471496582031s
Received healthy response to inference request in 1.2472996711730957s
Received healthy response to inference request in 1.2106478214263916s
Received healthy response to inference request in 1.266275405883789s
5 requests
0 failed requests
5th percentile: 1.2179781913757324
10th percentile: 1.2253085613250732
20th percentile: 1.239969301223755
30th percentile: 1.247349166870117
40th percentile: 1.2474481582641601
50th percentile: 1.2475471496582031
60th percentile: 1.2550384521484375
70th percentile: 1.2625297546386718
80th percentile: 1.4439186096191408
90th percentile: 1.799205017089844
95th percentile: 1.9768482208251952
99th percentile: 2.1189627838134766
mean time: 1.4252522945404054
Pipeline stage StressChecker completed in 7.73s
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
bbchicago-l3-8b-fusion-v0-0-0_v2 status is now deployed due to DeploymentManager action
bbchicago-l3-8b-fusion-v0-0-0_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics