bbchicago-brt-v1-12-narr_5229

developer_uid: Bbbrun0

submission_id: bbchicago-brt-v1-12-narr_5229_v2

model_name: best_of_4_reward_medium

model_group: BBChicago/Brt_v1.12_narr

status: torndown

timestamp: 2024-08-14T03:38:24+00:00

num_battles: 10852

num_wins: 5128

celo_rating: 1198.81

family_friendly_score: 0.0

submission_type: basic

model_repo: BBChicago/Brt_v1.12_narration_alignment_s1500

model_architecture: LlamaForCausalLM

reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: best_of_4_reward_medium

is_internal_developer: False

language_model: BBChicago/Brt_v1.12_narration_alignment_s1500

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-13

win_ratio: 0.47253962403243643

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-v1-12-narr-5229-v2-mkmlizer
Waiting for job on bbchicago-brt-v1-12-narr-5229-v2-mkmlizer to finish
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║     _____            __           __                                ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║       /___/                                                         ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  Version: 0.9.9                                                     ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  belonging to:                                                      ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ║                                                                     ║
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Downloaded to shared memory in 43.898s
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptjzwqhko, device:0
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-v1-12-narr-5229-v2
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-v1-12-narr-5229-v2/config.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-v1-12-narr-5229-v2/special_tokens_map.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-v1-12-narr-5229-v2/tokenizer_config.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-v1-12-narr-5229-v2/tokenizer.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-v1-12-narr-5229-v2/flywheel_model.0.safetensors
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 27.53it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.84it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.79it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 38.13it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 35.74it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:06, 39.70it/s]
Loading 0:  12%|█▏        | 35/291 [00:01<00:09, 27.67it/s]
Loading 0:  13%|█▎        | 39/291 [00:01<00:08, 28.18it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:08, 28.97it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.85it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.62it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.23it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.50it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.05it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.55it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.55it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.27it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.66it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.57it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.16it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.67it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.43it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.33it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.12it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.68it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.20it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.77it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.24it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.85it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.07it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.21it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.38it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.85it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.56it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 34.92it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 37.52it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.40it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.23it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.98it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.76it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.57it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.43it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.02it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.70it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.54it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.17it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.23it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.89it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.17it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 35.34it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.33it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.26it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.89it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.75it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.80it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.75it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.04it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.99it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.22it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.55it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.25it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:02,  2.46it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.05it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer:   warnings.warn(
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer:   warnings.warn(
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Saving duration: 0.340s
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.642s
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/config.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/special_tokens_map.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/tokenizer_config.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/merges.txt
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/vocab.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/tokenizer.json
bbchicago-brt-v1-12-narr-5229-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-v1-12-narr-5229-v2_reward/reward.tensors
Job bbchicago-brt-v1-12-narr-5229-v2-mkmlizer completed after 115.6s with status: succeeded
Stopping job with name bbchicago-brt-v1-12-narr-5229-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-v1-12-narr-5229-v2
Waiting for inference service bbchicago-brt-v1-12-narr-5229-v2 to be ready
Failed to get response for submission chaiml-elo-alignment-run-3_v17: ('http://chaiml-elo-alignment-run-3-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43182->127.0.0.1:8080: read: connection reset by peer\n')
Inference service bbchicago-brt-v1-12-narr-5229-v2 ready after 292.0068144798279s
Pipeline stage ISVCDeployer completed in 293.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.062546968460083s
Received healthy response to inference request in 1.2062931060791016s
Received healthy response to inference request in 1.181501865386963s
Received healthy response to inference request in 1.1575982570648193s
Received healthy response to inference request in 1.1663975715637207s
5 requests
0 failed requests
5th percentile: 1.1593581199645997
10th percentile: 1.1611179828643798
20th percentile: 1.1646377086639403
30th percentile: 1.1694184303283692
40th percentile: 1.175460147857666
50th percentile: 1.181501865386963
60th percentile: 1.1914183616638183
70th percentile: 1.2013348579406737
80th percentile: 1.377543878555298
90th percentile: 1.7200454235076905
95th percentile: 1.8912961959838865
99th percentile: 2.0282968139648436
mean time: 1.3548675537109376
Pipeline stage StressChecker completed in 8.39s
bbchicago-brt-v1-12-narr_5229_v2 status is now deployed due to DeploymentManager action
bbchicago-brt-v1-12-narr_5229_v2 status is now inactive due to auto deactivation removed underperforming models
bbchicago-brt-v1-12-narr_5229_v2 status is now torndown due to DeploymentManager action