chaiml-small-espresso-a_6112

developer_uid: azuruce

submission_id: chaiml-small-espresso-a_6112_v12

model_name: chaiml-small-espresso-a_6112_v12

model_group: ChaiML/small_espresso_an

status: inactive

timestamp: 2024-12-06T19:39:20+00:00

num_battles: 12770

num_wins: 6606

celo_rating: 1273.24

family_friendly_score: 0.5784

family_friendly_standard_error: 0.006983601363193635

submission_type: basic

model_repo: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3765215395910585, 'latency_mean': 2.6558310973644255, 'latency_p50': 2.6655062437057495, 'latency_p90': 2.9280800342559816}, {'batch_size': 2, 'throughput': 0.5995379686913404, 'latency_mean': 3.327380737066269, 'latency_p50': 3.31259822845459, 'latency_p90': 3.6602424144744874}, {'batch_size': 3, 'throughput': 0.7584917526591984, 'latency_mean': 3.9547908127307894, 'latency_p50': 3.927902340888977, 'latency_p90': 4.335462260246277}, {'batch_size': 4, 'throughput': 0.8776783756529275, 'latency_mean': 4.549140841960907, 'latency_p50': 4.546936392784119, 'latency_p90': 5.0031298160552975}, {'batch_size': 5, 'throughput': 0.9689368919018922, 'latency_mean': 5.139842587709427, 'latency_p50': 5.123869895935059, 'latency_p90': 5.690224766731262}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-espresso-a_6112_v12

is_internal_developer: True

language_model: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a

model_size: 22B

ranking_group: single

throughput_3p7s: 0.7

us_pacific_date: 2024-12-06

win_ratio: 0.5173061863743148

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '{memory}\n', 'prompt_template': '{prompt}\n', '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-small-espresso-a-6112-v12-mkmlizer
Waiting for job on chaiml-small-espresso-a-6112-v12-mkmlizer to finish
chaiml-small-espresso-a-6112-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-a-6112-v12-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ║                                                                     ║
chaiml-small-espresso-a-6112-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-espresso-a-6112-v12-mkmlizer: Downloaded to shared memory in 56.534s
chaiml-small-espresso-a-6112-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo826u7fs, device:0
chaiml-small-espresso-a-6112-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-espresso-a-6112-v12-mkmlizer: quantized model in 43.017s
chaiml-small-espresso-a-6112-v12-mkmlizer: Processed model ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 99.551s
chaiml-small-espresso-a-6112-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-a-6112-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-a-6112-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v12
chaiml-small-espresso-a-6112-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v12/special_tokens_map.json
chaiml-small-espresso-a-6112-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v12/config.json
chaiml-small-espresso-a-6112-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v12/flywheel_model.1.safetensors
chaiml-small-espresso-a-6112-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-espresso-a-6112-v12/flywheel_model.0.safetensors
chaiml-small-espresso-a-6112-v12-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.39it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.24it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.74it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.92it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.61it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 35.57it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 43.45it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 43.20it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 37.52it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:16, 27.95it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:15, 28.29it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 31.83it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.55it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 34.98it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.37it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 41.10it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 40.49it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.14it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 41.29it/s]
Loading 0:  21%|██        | 107/507 [00:02<00:11, 34.02it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 29.32it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 27.76it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.81it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.86it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 36.07it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 38.92it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 39.15it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:08, 40.44it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 40.91it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.75it/s]
Loading 0:  33%|███▎      | 165/507 [00:04<00:07, 43.55it/s]
Loading 0:  34%|███▎      | 170/507 [00:04<00:10, 32.32it/s]
Loading 0:  34%|███▍      | 174/507 [00:04<00:10, 32.71it/s]
Loading 0:  35%|███▌      | 178/507 [00:05<00:09, 33.13it/s]
Loading 0:  36%|███▋      | 184/507 [00:05<00:08, 37.01it/s]
Loading 0:  37%|███▋      | 189/507 [00:05<00:08, 39.68it/s]
Loading 0:  38%|███▊      | 194/507 [00:05<00:08, 35.10it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:07, 42.31it/s]
Loading 0:  41%|████      | 206/507 [00:05<00:07, 42.57it/s]
Loading 0:  42%|████▏     | 211/507 [00:05<00:07, 42.22it/s]
Loading 0:  43%|████▎     | 217/507 [00:05<00:06, 41.86it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:07, 40.26it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:08, 31.96it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 30.62it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 35.40it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.35it/s]
Loading 0:  49%|████▊     | 246/507 [00:06<00:06, 37.36it/s]
Loading 0:  49%|████▉     | 250/507 [00:06<00:06, 36.97it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 39.33it/s]
Loading 0:  51%|█████▏    | 260/507 [00:07<00:06, 39.39it/s]
Loading 0:  52%|█████▏    | 265/507 [00:07<00:06, 38.86it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 39.06it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:05, 39.78it/s]
Loading 0:  55%|█████▌    | 279/507 [00:07<00:05, 40.32it/s]
Loading 0:  56%|█████▌    | 284/507 [00:07<00:07, 29.18it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:07, 28.24it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 29.24it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:07, 29.24it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<02:51,  1.21it/s]
Loading 0:  60%|█████▉    | 302/507 [00:22<02:28,  1.38it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:39,  2.02it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:18,  2.50it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.45it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:37,  5.05it/s]
Loading 0:  64%|██████▍   | 325/507 [00:23<00:24,  7.49it/s]
Loading 0:  65%|██████▍   | 329/507 [00:23<00:19,  9.29it/s]
Loading 0:  66%|██████▌   | 335/507 [00:23<00:13, 13.22it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:11, 14.62it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:09, 17.00it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 18.88it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 24.93it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 27.25it/s]
Loading 0:  72%|███████▏  | 363/507 [00:24<00:04, 31.78it/s]
Loading 0:  73%|███████▎  | 368/507 [00:24<00:04, 33.91it/s]
Loading 0:  74%|███████▎  | 373/507 [00:24<00:03, 36.64it/s]
Loading 0:  75%|███████▍  | 379/507 [00:25<00:03, 38.23it/s]
Loading 0:  76%|███████▌  | 384/507 [00:25<00:03, 38.34it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:02, 40.94it/s]
Loading 0:  78%|███████▊  | 394/507 [00:25<00:02, 37.98it/s]
Loading 0:  79%|███████▊  | 399/507 [00:25<00:03, 32.90it/s]
Loading 0:  79%|███████▉  | 403/507 [00:25<00:03, 31.74it/s]
Loading 0:  80%|████████  | 408/507 [00:25<00:02, 34.75it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.78it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.39it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 37.11it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 40.30it/s]
Loading 0:  85%|████████▌ | 431/507 [00:26<00:01, 40.44it/s]
Loading 0:  86%|████████▌ | 436/507 [00:26<00:01, 41.65it/s]
Loading 0:  87%|████████▋ | 442/507 [00:26<00:01, 41.43it/s]
Loading 0:  88%|████████▊ | 447/507 [00:26<00:01, 37.82it/s]
Loading 0:  89%|████████▉ | 453/507 [00:26<00:01, 42.20it/s]
Loading 0:  90%|█████████ | 458/507 [00:29<00:07,  6.76it/s]
Loading 0:  91%|█████████ | 462/507 [00:29<00:05,  8.44it/s]
Loading 0:  92%|█████████▏| 466/507 [00:29<00:03, 10.38it/s]
Loading 0:  93%|█████████▎| 472/507 [00:29<00:02, 14.52it/s]
Loading 0:  94%|█████████▍| 476/507 [00:29<00:01, 17.06it/s]
Loading 0:  95%|█████████▍| 481/507 [00:29<00:01, 21.23it/s]
Loading 0:  96%|█████████▌| 485/507 [00:29<00:00, 23.70it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.63it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 29.20it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 32.90it/s]
Loading 0:  99%|█████████▉| 504/507 [00:30<00:00, 34.84it/s]
                                                            
Job chaiml-small-espresso-a-6112-v12-mkmlizer completed after 136.1s with status: succeeded
Stopping job with name chaiml-small-espresso-a-6112-v12-mkmlizer
Pipeline stage MKMLizer completed in 136.63s
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-small-espresso-a-6112-v12
Waiting for inference service chaiml-small-espresso-a-6112-v12 to be ready
Inference service chaiml-small-espresso-a-6112-v12 ready after 170.69558572769165s
Pipeline stage MKMLDeployer completed in 171.17s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.5569207668304443s
Received healthy response to inference request in 3.078524589538574s
Received healthy response to inference request in 2.7319352626800537s
Received healthy response to inference request in 2.7730295658111572s
5 requests
1 failed requests
5th percentile: 2.7401541233062745
10th percentile: 2.7483729839324953
20th percentile: 2.7648107051849364
30th percentile: 2.834128570556641
40th percentile: 2.9563265800476075
50th percentile: 3.078524589538574
60th percentile: 3.269883060455322
70th percentile: 3.46124153137207
80th percentile: 6.873304653167727
90th percentile: 13.506072425842287
95th percentile: 16.82245631217956
99th percentile: 19.47556342124939
mean time: 6.455850076675415
%s, retrying in %s seconds...
Received healthy response to inference request in 2.8889734745025635s
Received healthy response to inference request in 2.760166645050049s
Received healthy response to inference request in 2.823493003845215s
Received healthy response to inference request in 2.9032235145568848s
Received healthy response to inference request in 2.7158806324005127s
5 requests
0 failed requests
5th percentile: 2.72473783493042
10th percentile: 2.733595037460327
20th percentile: 2.7513094425201414
30th percentile: 2.772831916809082
40th percentile: 2.7981624603271484
50th percentile: 2.823493003845215
60th percentile: 2.8496851921081543
70th percentile: 2.8758773803710938
80th percentile: 2.891823482513428
90th percentile: 2.8975234985351563
95th percentile: 2.9003735065460203
99th percentile: 2.902653512954712
mean time: 2.818347454071045
Pipeline stage StressChecker completed in 49.37s
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 2.40s
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 2.46s
Shutdown handler de-registered
chaiml-small-espresso-a_6112_v12 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 3350.66s
Shutdown handler de-registered
chaiml-small-espresso-a_6112_v12 status is now inactive due to auto deactivation removed underperforming models