bbchicago-test-113k-dpo-_5640

developer_uid: Bbbrun0

submission_id: bbchicago-test-113k-dpo-_5640_v4

model_name: auto

model_group: BBChicago/test_113k_dpo_

status: torndown

timestamp: 2024-08-14T02:29:35+00:00

num_battles: 12208

num_wins: 5798

celo_rating: 1202.0

family_friendly_score: 0.0

submission_type: basic

model_repo: BBChicago/test_113k_dpo_steps3000

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: auto

is_internal_developer: False

language_model: BBChicago/test_113k_dpo_steps3000

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-13

win_ratio: 0.47493446920052423

generation_params: {'temperature': 0.95, 'top_p': 0.95, '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': "{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: {'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-test-113k-dpo-5640-v4-mkmlizer
Waiting for job on bbchicago-test-113k-dpo-5640-v4-mkmlizer to finish
Stopping job with name bbchicago-test-113k-dpo-5640-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name bbchicago-test-113k-dpo-5640-v4-mkmlizer
Waiting for job on bbchicago-test-113k-dpo-5640-v4-mkmlizer to finish
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║       /___/                                                         ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║                                                                     ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  Version: 0.9.9                                                     ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║                                                                     ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║                                                                     ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ║                                                                     ║
bbchicago-test-113k-dpo-5640-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Downloaded to shared memory in 68.202s
bbchicago-test-113k-dpo-5640-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptz0l76vp, device:0
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-test-113k-dpo-5640-v4-mkmlizer: quantized model in 28.482s
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Processed model BBChicago/test_113k_dpo_steps3000 in 96.684s
bbchicago-test-113k-dpo-5640-v4-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-113k-dpo-5640-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-113k-dpo-5640-v4
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-113k-dpo-5640-v4/config.json
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-113k-dpo-5640-v4/special_tokens_map.json
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-113k-dpo-5640-v4/tokenizer_config.json
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-113k-dpo-5640-v4/tokenizer.json
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-113k-dpo-5640-v4/flywheel_model.0.safetensors
bbchicago-test-113k-dpo-5640-v4-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
bbchicago-test-113k-dpo-5640-v4-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, 37.43it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.85it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.96it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 35.68it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 41.64it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.06it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.94it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.91it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.12it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 35.21it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.25it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 35.88it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.76it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.09it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.39it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.52it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 27.30it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.77it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.36it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.47it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.64it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.42it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.10it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.12it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.44it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.30it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.95it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.27it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.47it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.37it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.95it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 36.88it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 35.43it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 37.66it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.88it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.16it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.73it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 41.18it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 25.81it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 26.91it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.41it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.80it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 35.59it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.45it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.16it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.50it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.26it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 35.44it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.46it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.04it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.65it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.04it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.96it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.53it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 36.91it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.51it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 38.21it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.09it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 33.98it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.22it/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-test-113k-dpo-5640-v4-mkmlizer:   warnings.warn(
bbchicago-test-113k-dpo-5640-v4-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-test-113k-dpo-5640-v4-mkmlizer:   warnings.warn(
bbchicago-test-113k-dpo-5640-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-113k-dpo-5640-v4-mkmlizer:   warnings.warn(
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Saving duration: 0.324s
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.596s
bbchicago-test-113k-dpo-5640-v4-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-113k-dpo-5640-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-113k-dpo-5640-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-113k-dpo-5640-v4_reward
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-113k-dpo-5640-v4_reward/config.json
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-113k-dpo-5640-v4_reward/special_tokens_map.json
bbchicago-test-113k-dpo-5640-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-113k-dpo-5640-v4_reward/tokenizer_config.json
Job bbchicago-test-113k-dpo-5640-v4-mkmlizer completed after 133.11s with status: succeeded
Stopping job with name bbchicago-test-113k-dpo-5640-v4-mkmlizer
Pipeline stage MKMLizer completed in 137.06s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-113k-dpo-5640-v4
Waiting for inference service bbchicago-test-113k-dpo-5640-v4 to be ready
Inference service bbchicago-test-113k-dpo-5640-v4 ready after 281.1304476261139s
Pipeline stage ISVCDeployer completed in 283.47s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.269334316253662s
Received healthy response to inference request in 1.2373576164245605s
Received healthy response to inference request in 1.2230923175811768s
Received healthy response to inference request in 1.21498703956604s
Received healthy response to inference request in 1.2296791076660156s
5 requests
0 failed requests
5th percentile: 1.2166080951690674
10th percentile: 1.2182291507720948
20th percentile: 1.2214712619781494
30th percentile: 1.2244096755981446
40th percentile: 1.2270443916320801
50th percentile: 1.2296791076660156
60th percentile: 1.2327505111694337
70th percentile: 1.2358219146728515
80th percentile: 1.443752956390381
90th percentile: 1.8565436363220216
95th percentile: 2.0629389762878416
99th percentile: 2.228055248260498
mean time: 1.434890079498291
Pipeline stage StressChecker completed in 7.92s
bbchicago-test-113k-dpo-_5640_v4 status is now deployed due to DeploymentManager action
bbchicago-test-113k-dpo-_5640_v4 status is now inactive due to auto deactivation removed underperforming models
bbchicago-test-113k-dpo-_5640_v4 status is now torndown due to DeploymentManager action