chaiml-espresso-ant-2412_1172

developer_uid: azuruce

submission_id: chaiml-espresso-ant-2412_1172_v2

model_name: chaiml-espresso-ant-2412_1172_v2

model_group: ChaiML/espresso_ant_2412

status: torndown

timestamp: 2024-12-04T17:06:37+00:00

num_battles: 17644

num_wins: 9023

celo_rating: 1269.45

family_friendly_score: 0.5860000000000001

family_friendly_standard_error: 0.006965687331484238

submission_type: basic

model_repo: ChaiML/espresso_ant_241204_albert_v1

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3829091852965761, 'latency_mean': 2.6114999294281005, 'latency_p50': 2.6362950801849365, 'latency_p90': 2.8943422555923464}, {'batch_size': 2, 'throughput': 0.6005157370498136, 'latency_mean': 3.326561806201935, 'latency_p50': 3.3316115140914917, 'latency_p90': 3.6307076454162597}, {'batch_size': 3, 'throughput': 0.7644744067853403, 'latency_mean': 3.9086091327667236, 'latency_p50': 3.8961687088012695, 'latency_p90': 4.375292158126831}, {'batch_size': 4, 'throughput': 0.8861465128080063, 'latency_mean': 4.502108849287033, 'latency_p50': 4.485503792762756, 'latency_p90': 5.031280660629273}, {'batch_size': 5, 'throughput': 0.985415829095532, 'latency_mean': 5.05006195306778, 'latency_p50': 5.062853455543518, 'latency_p90': 5.766702818870544}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-2412_1172_v2

is_internal_developer: True

language_model: ChaiML/espresso_ant_241204_albert_v1

model_size: 22B

ranking_group: single

throughput_3p7s: 0.71

us_pacific_date: 2024-12-04

win_ratio: 0.5113919746089323

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': '', '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-ant-2412-1172-v2-mkmlizer
Waiting for job on chaiml-espresso-ant-2412-1172-v2-mkmlizer to finish
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-2412-1172-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-2412-1172-v2-mkmlizer: Downloaded to shared memory in 62.423s
chaiml-espresso-ant-2412-1172-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp90fg5k8_, device:0
chaiml-espresso-ant-2412-1172-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-2412-1172-v2-mkmlizer: quantized model in 45.997s
chaiml-espresso-ant-2412-1172-v2-mkmlizer: Processed model ChaiML/espresso_ant_241204_albert_v1 in 108.420s
chaiml-espresso-ant-2412-1172-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-2412-1172-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-2412-1172-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2
chaiml-espresso-ant-2412-1172-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2/config.json
chaiml-espresso-ant-2412-1172-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2/special_tokens_map.json
chaiml-espresso-ant-2412-1172-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2/tokenizer_config.json
chaiml-espresso-ant-2412-1172-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2/tokenizer.json
chaiml-espresso-ant-2412-1172-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2/flywheel_model.1.safetensors
chaiml-espresso-ant-2412-1172-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-2412-1172-v2/flywheel_model.0.safetensors
chaiml-espresso-ant-2412-1172-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:22, 22.08it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:13, 37.37it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.46it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:13, 36.53it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:13, 36.73it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 36.79it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:13, 35.57it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:12, 36.24it/s]
Loading 0:   9%|▉         | 45/507 [00:01<00:11, 38.73it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:14, 31.45it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:20, 22.13it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:21, 21.11it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:15, 28.71it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 29.26it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 33.54it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 37.41it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:12, 34.71it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:12, 33.46it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:13, 31.29it/s]
Loading 0:  19%|█▊        | 95/507 [00:02<00:12, 32.75it/s]
Loading 0:  20%|█▉        | 99/507 [00:03<00:13, 29.27it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:11, 33.78it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 33.22it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:16, 24.35it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.63it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:15, 25.03it/s]
Loading 0:  25%|██▌       | 129/507 [00:04<00:12, 31.28it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:12, 31.15it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.08it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 33.78it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 37.00it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 35.88it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.22it/s]
Loading 0:  32%|███▏      | 160/507 [00:05<00:09, 36.32it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 36.76it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.83it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.86it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.19it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.12it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.01it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:08, 36.58it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:08, 35.35it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 38.08it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 36.65it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 39.56it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 38.71it/s]
Loading 0:  43%|████▎     | 219/507 [00:06<00:08, 32.25it/s]
Loading 0:  44%|████▍     | 224/507 [00:07<00:10, 25.97it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 27.16it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 33.38it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.01it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.55it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.33it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.70it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.09it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 38.23it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 36.41it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 37.45it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 34.49it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 37.27it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 23.65it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 26.46it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:07, 26.46it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<02:59,  1.16it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:36,  1.31it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:45,  1.90it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:23,  2.35it/s]
Loading 0:  62%|██████▏   | 314/507 [00:25<00:59,  3.24it/s]
Loading 0:  63%|██████▎   | 319/507 [00:25<00:39,  4.73it/s]
Loading 0:  64%|██████▍   | 324/507 [00:25<00:27,  6.73it/s]
Loading 0:  65%|██████▍   | 328/507 [00:25<00:20,  8.66it/s]
Loading 0:  66%|██████▌   | 333/507 [00:25<00:14, 11.80it/s]
Loading 0:  67%|██████▋   | 338/507 [00:26<00:10, 15.57it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:10, 15.19it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:09, 17.02it/s]
Loading 0:  70%|██████▉   | 354/507 [00:26<00:06, 24.01it/s]
Loading 0:  71%|███████   | 359/507 [00:26<00:05, 26.78it/s]
Loading 0:  72%|███████▏  | 364/507 [00:26<00:04, 29.86it/s]
Loading 0:  73%|███████▎  | 369/507 [00:27<00:04, 32.93it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:04, 30.99it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 38.60it/s]
Loading 0:  76%|███████▌  | 386/507 [00:27<00:03, 38.14it/s]
Loading 0:  77%|███████▋  | 391/507 [00:27<00:03, 32.60it/s]
Loading 0:  78%|███████▊  | 395/507 [00:27<00:04, 25.86it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:03, 27.53it/s]
Loading 0:  80%|████████  | 408/507 [00:28<00:02, 33.51it/s]
Loading 0:  81%|████████▏ | 412/507 [00:28<00:02, 33.02it/s]
Loading 0:  82%|████████▏ | 417/507 [00:28<00:02, 35.97it/s]
Loading 0:  83%|████████▎ | 421/507 [00:28<00:02, 35.72it/s]
Loading 0:  84%|████████▍ | 426/507 [00:28<00:02, 38.28it/s]
Loading 0:  85%|████████▌ | 431/507 [00:28<00:02, 37.13it/s]
Loading 0:  86%|████████▌ | 435/507 [00:28<00:01, 37.37it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 35.00it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 37.66it/s]
Loading 0:  88%|████████▊ | 448/507 [00:29<00:01, 35.30it/s]
Loading 0:  90%|████████▉ | 454/507 [00:29<00:01, 37.64it/s]
Loading 0:  90%|█████████ | 458/507 [00:31<00:08,  6.07it/s]
Loading 0:  91%|█████████ | 461/507 [00:31<00:06,  7.27it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  9.16it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.08it/s]
Loading 0:  94%|█████████▍| 476/507 [00:32<00:01, 16.41it/s]
Loading 0:  95%|█████████▍| 481/507 [00:32<00:01, 20.52it/s]
Loading 0:  96%|█████████▌| 485/507 [00:32<00:00, 23.12it/s]
Loading 0:  97%|█████████▋| 490/507 [00:32<00:00, 27.12it/s]
Loading 0:  97%|█████████▋| 494/507 [00:32<00:00, 28.96it/s]
Loading 0:  98%|█████████▊| 499/507 [00:32<00:00, 32.81it/s]
Loading 0:  99%|█████████▉| 503/507 [00:32<00:00, 33.68it/s]
                                                            
Job chaiml-espresso-ant-2412-1172-v2-mkmlizer completed after 145.73s with status: succeeded
Stopping job with name chaiml-espresso-ant-2412-1172-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-2412-1172-v2
Waiting for inference service chaiml-espresso-ant-2412-1172-v2 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-ant-2412-1172-v2 ready after 200.70711302757263s
Pipeline stage MKMLDeployer completed in 201.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.968388319015503s
Received healthy response to inference request in 2.4016427993774414s
Received healthy response to inference request in 2.3229033946990967s
Received healthy response to inference request in 2.64919114112854s
Received healthy response to inference request in 2.540314197540283s
5 requests
0 failed requests
5th percentile: 2.3386512756347657
10th percentile: 2.3543991565704347
20th percentile: 2.3858949184417724
30th percentile: 2.4293770790100098
40th percentile: 2.4848456382751465
50th percentile: 2.540314197540283
60th percentile: 2.5838649749755858
70th percentile: 2.6274157524108888
80th percentile: 2.7130305767059326
90th percentile: 2.8407094478607178
95th percentile: 2.9045488834381104
99th percentile: 2.9556204319000243
mean time: 2.576487970352173
Pipeline stage StressChecker completed in 14.74s
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 2.19s
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 2.23s
Shutdown handler de-registered
chaiml-espresso-ant-2412_1172_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-espresso-ant-2412-1172-v2-profiler
Waiting for inference service chaiml-espresso-ant-2412-1172-v2-profiler to be ready
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 3205.72s
Shutdown handler de-registered
chaiml-espresso-ant-2412_1172_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-espresso-ant-2412_1172_v2 status is now torndown due to DeploymentManager action
chaiml-espresso-ant-2412_1172_v2 status is now torndown due to DeploymentManager action
chaiml-espresso-ant-2412_1172_v2 status is now torndown due to DeploymentManager action