chaiml-espresso-story-24_3275

developer_uid: azuruce

submission_id: chaiml-espresso-story-24_3275_v1

model_name: chaiml-espresso-story-24_3275_v1

model_group: ChaiML/espresso_story_24

status: inactive

timestamp: 2024-12-06T01:41:04+00:00

num_battles: 9334

num_wins: 4630

celo_rating: 1262.1

family_friendly_score: 0.5822

family_friendly_standard_error: 0.006974857131153297

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': 0.3911506005775177, 'latency_mean': 2.5564978444576263, 'latency_p50': 2.5544018745422363, 'latency_p90': 2.8374040126800537}, {'batch_size': 3, 'throughput': 0.8272117469170607, 'latency_mean': 3.6146079206466677, 'latency_p50': 3.626592755317688, 'latency_p90': 4.0160833358764645}, {'batch_size': 5, 'throughput': 1.0805705332262183, 'latency_mean': 4.59848886847496, 'latency_p50': 4.6477179527282715, 'latency_p90': 5.142611145973206}, {'batch_size': 6, 'throughput': 1.1789393213372266, 'latency_mean': 5.063982266187668, 'latency_p50': 5.073519825935364, 'latency_p90': 5.537227511405945}, {'batch_size': 10, 'throughput': 1.382738235799386, 'latency_mean': 7.159041579961777, 'latency_p50': 7.154946446418762, 'latency_p90': 8.059240770339965}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-story-24_3275_v1

is_internal_developer: True

language_model: ChaiML/espresso_story_241205_albert_v1_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2024-12-05

win_ratio: 0.4960359974287551

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-v1-mkmlizer
Waiting for job on chaiml-espresso-story-24-3275-v1-mkmlizer to finish
chaiml-espresso-story-24-3275-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-story-24-3275-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-story-24-3275-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-story-24-3275-v1-mkmlizer: Downloaded to shared memory in 75.818s
chaiml-espresso-story-24-3275-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqe25f0_y, device:0
chaiml-espresso-story-24-3275-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-story-24-3275-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-story-24-3275-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-story-24-3275-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v1
chaiml-espresso-story-24-3275-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v1/config.json
chaiml-espresso-story-24-3275-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v1/special_tokens_map.json
chaiml-espresso-story-24-3275-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v1/tokenizer_config.json
chaiml-espresso-story-24-3275-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v1/tokenizer.json
chaiml-espresso-story-24-3275-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-story-24-3275-v1/flywheel_model.0.safetensors
chaiml-espresso-story-24-3275-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/507 [00:00<00:12, 39.97it/s]
Loading 0:   2%|▏         | 8/507 [00:00<00:16, 31.17it/s]
Loading 0:   3%|▎         | 13/507 [00:00<00:14, 35.14it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:14, 33.34it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:14, 33.54it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:15, 31.32it/s]
Loading 0:   6%|▌         | 29/507 [00:00<00:14, 33.54it/s]
Loading 0:   7%|▋         | 33/507 [00:01<00:15, 29.71it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:13, 35.55it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 35.22it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 36.05it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 35.36it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:20, 22.55it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:19, 22.77it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:18, 23.79it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 23.11it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 27.41it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:15, 27.70it/s]
Loading 0:  16%|█▌        | 79/507 [00:02<00:12, 35.18it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:12, 32.86it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:13, 32.02it/s]
Loading 0:  18%|█▊        | 91/507 [00:03<00:13, 29.89it/s]
Loading 0:  19%|█▊        | 95/507 [00:03<00:13, 31.20it/s]
Loading 0:  20%|█▉        | 99/507 [00:03<00:14, 27.38it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:14, 28.79it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:15, 25.99it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:13, 29.79it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:20, 18.84it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:17, 22.03it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:14, 25.89it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:15, 24.13it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:13, 27.57it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:14, 25.90it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:12, 29.68it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:13, 26.86it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:11, 30.19it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:12, 27.27it/s]
Loading 0:  32%|███▏      | 163/507 [00:05<00:11, 31.00it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:10, 31.65it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:16, 20.65it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:15, 20.76it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:13, 24.81it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:13, 23.92it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:11, 27.63it/s]
Loading 0:  38%|███▊      | 194/507 [00:07<00:11, 26.13it/s]
Loading 0:  39%|███▉      | 199/507 [00:07<00:10, 30.47it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:10, 28.75it/s]
Loading 0:  41%|████▏     | 210/507 [00:07<00:08, 36.12it/s]
Loading 0:  42%|████▏     | 214/507 [00:07<00:08, 35.08it/s]
Loading 0:  43%|████▎     | 218/507 [00:07<00:08, 35.28it/s]
Loading 0:  44%|████▍     | 222/507 [00:07<00:08, 35.30it/s]
Loading 0:  45%|████▍     | 226/507 [00:08<00:11, 25.38it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:10, 25.22it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:09, 30.05it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:09, 28.25it/s]
Loading 0:  49%|████▊     | 246/507 [00:08<00:07, 34.68it/s]
Loading 0:  49%|████▉     | 250/507 [00:08<00:07, 33.59it/s]
Loading 0:  50%|█████     | 255/507 [00:08<00:06, 36.04it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 34.67it/s]
Loading 0:  52%|█████▏    | 264/507 [00:09<00:06, 36.41it/s]
Loading 0:  53%|█████▎    | 268/507 [00:09<00:07, 33.38it/s]
Loading 0:  54%|█████▎    | 272/507 [00:09<00:06, 33.83it/s]
Loading 0:  54%|█████▍    | 276/507 [00:09<00:07, 29.81it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:07, 31.37it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:09, 22.94it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:10, 21.15it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 24.09it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:07, 28.06it/s]
Loading 0:  59%|█████▉    | 299/507 [00:25<00:07, 28.06it/s]
Loading 0:  59%|█████▉    | 300/507 [00:25<04:10,  1.21s/it]
Loading 0:  60%|█████▉    | 302/507 [00:25<03:25,  1.00s/it]
Loading 0:  61%|██████    | 307/507 [00:25<02:04,  1.61it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:33,  2.11it/s]
Loading 0:  62%|██████▏   | 313/507 [00:26<01:09,  2.79it/s]
Loading 0:  63%|██████▎   | 318/507 [00:26<00:43,  4.36it/s]
Loading 0:  63%|██████▎   | 321/507 [00:26<00:33,  5.49it/s]
Loading 0:  64%|██████▍   | 327/507 [00:26<00:20,  8.74it/s]
Loading 0:  65%|██████▌   | 331/507 [00:26<00:16, 10.89it/s]
Loading 0:  66%|██████▌   | 335/507 [00:26<00:12, 13.50it/s]
Loading 0:  67%|██████▋   | 340/507 [00:26<00:11, 14.80it/s]
Loading 0:  68%|██████▊   | 343/507 [00:27<00:10, 16.00it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:09, 17.63it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:06, 22.66it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:06, 23.14it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:05, 27.92it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 26.26it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 30.37it/s]
Loading 0:  74%|███████▍  | 374/507 [00:28<00:04, 28.74it/s]
Loading 0:  75%|███████▌  | 381/507 [00:28<00:03, 36.62it/s]
Loading 0:  76%|███████▌  | 386/507 [00:28<00:03, 35.98it/s]
Loading 0:  77%|███████▋  | 390/507 [00:28<00:03, 29.71it/s]
Loading 0:  78%|███████▊  | 395/507 [00:28<00:04, 25.55it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:03, 27.14it/s]
Loading 0:  80%|████████  | 408/507 [00:29<00:02, 33.53it/s]
Loading 0:  81%|████████▏ | 412/507 [00:29<00:02, 33.05it/s]
Loading 0:  82%|████████▏ | 417/507 [00:29<00:02, 35.32it/s]
Loading 0:  83%|████████▎ | 421/507 [00:29<00:02, 34.43it/s]
Loading 0:  84%|████████▍ | 426/507 [00:29<00:02, 36.38it/s]
Loading 0:  85%|████████▍ | 430/507 [00:29<00:02, 33.94it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:01, 36.60it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 35.90it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 39.01it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 37.47it/s]
Loading 0:  90%|████████▉ | 454/507 [00:30<00:01, 39.09it/s]
Loading 0:  90%|█████████ | 458/507 [00:32<00:07,  6.23it/s]
Loading 0:  91%|█████████ | 461/507 [00:32<00:06,  7.45it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  9.41it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.40it/s]
Loading 0:  94%|█████████▍| 476/507 [00:33<00:01, 16.62it/s]
Loading 0:  95%|█████████▍| 481/507 [00:33<00:01, 20.54it/s]
Loading 0:  96%|█████████▌| 485/507 [00:33<00:00, 22.21it/s]
Loading 0:  97%|█████████▋| 490/507 [00:33<00:00, 25.82it/s]
Loading 0:  97%|█████████▋| 494/507 [00:33<00:00, 26.76it/s]
Loading 0:  98%|█████████▊| 499/507 [00:33<00:00, 29.85it/s]
Loading 0:  99%|█████████▉| 503/507 [00:33<00:00, 29.72it/s]
                                                            
Job chaiml-espresso-story-24-3275-v1-mkmlizer completed after 157.5s with status: succeeded
Stopping job with name chaiml-espresso-story-24-3275-v1-mkmlizer
Pipeline stage MKMLizer completed in 160.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-story-24-3275-v1
Waiting for inference service chaiml-espresso-story-24-3275-v1 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
Inference service chaiml-espresso-story-24-3275-v1 ready after 184.89296698570251s
Pipeline stage MKMLDeployer completed in 187.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5449957847595215s
Received healthy response to inference request in 2.389087438583374s
Received healthy response to inference request in 3.2126848697662354s
Received healthy response to inference request in 2.7293825149536133s
Received healthy response to inference request in 2.4094324111938477s
5 requests
0 failed requests
5th percentile: 2.3931564331054687
10th percentile: 2.3972254276275633
20th percentile: 2.405363416671753
30th percentile: 2.4734224319458007
40th percentile: 2.601402473449707
50th percentile: 2.7293825149536133
60th percentile: 2.9227034568786623
70th percentile: 3.116024398803711
80th percentile: 3.2791470527648925
90th percentile: 3.412071418762207
95th percentile: 3.4785336017608643
99th percentile: 3.53170334815979
mean time: 2.8571166038513183
Pipeline stage StressChecker completed in 15.66s
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 2.21s
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 2.05s
Shutdown handler de-registered
chaiml-espresso-story-24_3275_v1 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 3083.46s
Shutdown handler de-registered
chaiml-espresso-story-24_3275_v1 status is now inactive due to auto deactivation removed underperforming models