chaiml-espresso-story-24_3275

developer_uid: azuruce

submission_id: chaiml-espresso-story-24_3275_v5

model_name: chaiml-espresso-story-24_3275_v5

model_group: ChaiML/espresso_story_24

status: inactive

timestamp: 2024-12-06T06:57:46+00:00

num_battles: 11878

num_wins: 5863

celo_rating: 1249.75

family_friendly_score: 0.5862

family_friendly_standard_error: 0.006965192890365636

submission_type: basic

model_repo: ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3822600584413946, 'latency_mean': 2.6159531021118165, 'latency_p50': 2.629502296447754, 'latency_p90': 2.849087882041931}, {'batch_size': 3, 'throughput': 0.8129660359141606, 'latency_mean': 3.674263187646866, 'latency_p50': 3.6614668369293213, 'latency_p90': 4.033255529403687}, {'batch_size': 5, 'throughput': 1.0807793639617833, 'latency_mean': 4.594176042079925, 'latency_p50': 4.596413254737854, 'latency_p90': 5.186897110939026}, {'batch_size': 6, 'throughput': 1.165963482126951, 'latency_mean': 5.108788787126541, 'latency_p50': 5.110271334648132, 'latency_p90': 5.725184631347656}, {'batch_size': 10, 'throughput': 1.377847681999497, 'latency_mean': 7.211193174123764, 'latency_p50': 7.215689539909363, 'latency_p90': 8.072272396087646}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-story-24_3275_v5

is_internal_developer: True

language_model: ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-12-05

win_ratio: 0.49360161643374306

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-espresso-story-24-3275-v5-mkmlizer
Waiting for job on chaiml-espresso-story-24-3275-v5-mkmlizer to finish
chaiml-espresso-story-24-3275-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-story-24-3275-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-story-24-3275-v5-mkmlizer: quantized model in 43.434s
chaiml-espresso-story-24-3275-v5-mkmlizer: Processed model ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha in 88.989s
chaiml-espresso-story-24-3275-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-story-24-3275-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-story-24-3275-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v5
chaiml-espresso-story-24-3275-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v5/config.json
chaiml-espresso-story-24-3275-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v5/special_tokens_map.json
chaiml-espresso-story-24-3275-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v5/tokenizer_config.json
chaiml-espresso-story-24-3275-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v5/tokenizer.json
chaiml-espresso-story-24-3275-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v5/flywheel_model.1.safetensors
chaiml-espresso-story-24-3275-v5-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 22.82it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.96it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.02it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 37.33it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 37.90it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 38.84it/s]
Loading 0:   7%|▋         | 36/507 [00:00<00:11, 40.91it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:13, 34.97it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:11, 40.69it/s]
Loading 0:  10%|█         | 52/507 [00:01<00:12, 37.69it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 22.97it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 29.96it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.98it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 34.00it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.06it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 41.23it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.39it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 39.56it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 41.03it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:11, 34.92it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 28.80it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 27.47it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.53it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.18it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 35.10it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 38.21it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 37.37it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 38.58it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 40.34it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.29it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:08, 40.71it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:10, 30.91it/s]
Loading 0:  34%|███▍      | 173/507 [00:04<00:10, 31.28it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:10, 30.40it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.92it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:08, 35.63it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 39.07it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:07, 39.29it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:07, 39.82it/s]
Loading 0:  41%|████      | 207/507 [00:05<00:07, 41.50it/s]
Loading 0:  42%|████▏     | 212/507 [00:06<00:08, 35.78it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:06, 41.47it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 38.12it/s]
Loading 0:  45%|████▍     | 228/507 [00:06<00:09, 30.31it/s]
Loading 0:  46%|████▌     | 232/507 [00:06<00:09, 30.27it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:08, 33.37it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:08, 32.72it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.57it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.92it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.75it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.02it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.07it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 36.79it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 37.74it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 37.03it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 39.69it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.98it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.50it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.50it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:45,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:24,  1.42it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.05it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.53it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.48it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:37,  5.07it/s]
Loading 0:  64%|██████▍   | 325/507 [00:23<00:24,  7.49it/s]
Loading 0:  65%|██████▍   | 329/507 [00:24<00:19,  9.29it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 13.24it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:11, 14.77it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:09, 17.12it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 18.84it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 24.09it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 26.14it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.54it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.75it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.92it/s]
Loading 0:  74%|███████▍  | 377/507 [00:25<00:03, 37.52it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 39.03it/s]
Loading 0:  77%|███████▋  | 388/507 [00:25<00:02, 39.68it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:02, 38.68it/s]
Loading 0:  79%|███████▊  | 398/507 [00:26<00:03, 30.30it/s]
Loading 0:  79%|███████▉  | 402/507 [00:26<00:03, 29.30it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 34.52it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.74it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.70it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 36.82it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 40.08it/s]
Loading 0:  85%|████████▌ | 431/507 [00:26<00:01, 40.11it/s]
Loading 0:  86%|████████▌ | 436/507 [00:26<00:01, 40.85it/s]
Loading 0:  87%|████████▋ | 442/507 [00:27<00:01, 40.86it/s]
Loading 0:  88%|████████▊ | 447/507 [00:27<00:01, 39.71it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 43.95it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:06,  6.87it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:04,  9.31it/s]
Loading 0:  93%|█████████▎| 472/507 [00:29<00:02, 13.19it/s]
Loading 0:  94%|█████████▍| 477/507 [00:30<00:01, 15.91it/s]
Loading 0:  95%|█████████▌| 482/507 [00:30<00:01, 19.16it/s]
Loading 0:  96%|█████████▌| 487/507 [00:30<00:00, 22.98it/s]
Loading 0:  97%|█████████▋| 492/507 [00:30<00:00, 23.81it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 30.37it/s]
Loading 0:  99%|█████████▉| 504/507 [00:30<00:00, 32.29it/s]
                                                            
Job chaiml-espresso-story-24-3275-v5-mkmlizer completed after 124.19s with status: succeeded
Stopping job with name chaiml-espresso-story-24-3275-v5-mkmlizer
Pipeline stage MKMLizer completed in 126.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-story-24-3275-v5
Waiting for inference service chaiml-espresso-story-24-3275-v5 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-espresso-story-24-3275-v5 ready after 183.49671339988708s
Pipeline stage MKMLDeployer completed in 185.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6287145614624023s
Received healthy response to inference request in 2.3627617359161377s
Received healthy response to inference request in 2.2123520374298096s
Received healthy response to inference request in 2.2864484786987305s
Received healthy response to inference request in 2.3928229808807373s
5 requests
0 failed requests
5th percentile: 2.2271713256835937
10th percentile: 2.2419906139373778
20th percentile: 2.2716291904449464
30th percentile: 2.3017111301422117
40th percentile: 2.3322364330291747
50th percentile: 2.3627617359161377
60th percentile: 2.3747862339019776
70th percentile: 2.3868107318878176
80th percentile: 2.44000129699707
90th percentile: 2.5343579292297362
95th percentile: 2.5815362453460695
99th percentile: 2.619278898239136
mean time: 2.3766199588775634
Pipeline stage StressChecker completed in 13.23s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.41s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.32s
Shutdown handler de-registered
chaiml-espresso-story-24_3275_v5 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3115.74s
Shutdown handler de-registered
chaiml-espresso-story-24_3275_v5 status is now inactive due to auto deactivation removed underperforming models