chaiml-nemo-small-merge-_7220

developer_uid: azuruce

submission_id: chaiml-nemo-small-merge-_7220_v1

model_name: chaiml-nemo-small-merge-_7220_v1

model_group: ChaiML/nemo-small-merge-

status: inactive

timestamp: 2024-11-28T16:51:06+00:00

num_battles: 19520

num_wins: 9915

celo_rating: 1269.42

family_friendly_score: 0.5953999999999999

family_friendly_standard_error: 0.006941164743758788

submission_type: basic

model_repo: ChaiML/nemo-small-merge-3-albert

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38410991623859964, 'latency_mean': 2.603344283103943, 'latency_p50': 2.595532178878784, 'latency_p90': 2.870858001708984}, {'batch_size': 3, 'throughput': 0.8187656128593463, 'latency_mean': 3.655011693239212, 'latency_p50': 3.630208969116211, 'latency_p90': 4.103155970573425}, {'batch_size': 5, 'throughput': 1.0759610817015877, 'latency_mean': 4.600025241374969, 'latency_p50': 4.618702292442322, 'latency_p90': 5.143783068656921}, {'batch_size': 6, 'throughput': 1.158583348457841, 'latency_mean': 5.146792787313461, 'latency_p50': 5.186148047447205, 'latency_p90': 5.878071975708008}, {'batch_size': 10, 'throughput': 1.3865646578139839, 'latency_mean': 7.157736020088196, 'latency_p50': 7.137014269828796, 'latency_p90': 8.038891124725343}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-nemo-small-merge-_7220_v1

is_internal_developer: True

language_model: ChaiML/nemo-small-merge-3-albert

model_size: 22B

ranking_group: single

throughput_3p7s: 0.84

us_pacific_date: 2024-11-28

win_ratio: 0.5079405737704918

generation_params: {'temperature': 0.9, '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-nemo-small-merge-7220-v1-mkmlizer
Waiting for job on chaiml-nemo-small-merge-7220-v1-mkmlizer to finish
chaiml-nemo-small-merge-7220-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-small-merge-7220-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-nemo-small-merge-7220-v1-mkmlizer: Downloaded to shared memory in 91.979s
chaiml-nemo-small-merge-7220-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmj0cg67e, device:0
chaiml-nemo-small-merge-7220-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-small-merge-7220-v1-mkmlizer: quantized model in 44.496s
chaiml-nemo-small-merge-7220-v1-mkmlizer: Processed model ChaiML/nemo-small-merge-3-albert in 136.475s
chaiml-nemo-small-merge-7220-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-small-merge-7220-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-small-merge-7220-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/config.json
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/special_tokens_map.json
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/tokenizer_config.json
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/tokenizer.model
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/flywheel_model.1.safetensors
chaiml-nemo-small-merge-7220-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-small-merge-7220-v1/flywheel_model.0.safetensors
chaiml-nemo-small-merge-7220-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/507 [00:01<07:47,  1.08it/s]
Loading 0:   1%|          | 6/507 [00:02<02:17,  3.64it/s]
Loading 0:   3%|▎         | 13/507 [00:02<00:53,  9.21it/s]
Loading 0:   3%|▎         | 17/507 [00:02<00:40, 12.17it/s]
Loading 0:   4%|▍         | 22/507 [00:02<00:28, 16.73it/s]
Loading 0:   5%|▌         | 26/507 [00:02<00:24, 19.42it/s]
Loading 0:   6%|▌         | 31/507 [00:02<00:19, 23.83it/s]
Loading 0:   7%|▋         | 35/507 [00:02<00:18, 25.86it/s]
Loading 0:   8%|▊         | 40/507 [00:02<00:15, 29.94it/s]
Loading 0:   9%|▊         | 44/507 [00:03<00:15, 30.63it/s]
Loading 0:  10%|▉         | 49/507 [00:03<00:13, 32.94it/s]
Loading 0:  10%|█         | 53/507 [00:03<00:19, 22.90it/s]
Loading 0:  11%|█▏        | 58/507 [00:03<00:17, 26.12it/s]
Loading 0:  12%|█▏        | 62/507 [00:03<00:16, 27.08it/s]
Loading 0:  13%|█▎        | 67/507 [00:03<00:14, 30.92it/s]
Loading 0:  14%|█▍        | 71/507 [00:03<00:13, 31.66it/s]
Loading 0:  15%|█▍        | 76/507 [00:04<00:12, 34.07it/s]
Loading 0:  16%|█▌        | 80/507 [00:04<00:12, 34.13it/s]
Loading 0:  17%|█▋        | 85/507 [00:04<00:11, 36.68it/s]
Loading 0:  18%|█▊        | 89/507 [00:04<00:11, 35.83it/s]
Loading 0:  19%|█▊        | 94/507 [00:04<00:11, 36.69it/s]
Loading 0:  19%|█▉        | 98/507 [00:04<00:11, 34.59it/s]
Loading 0:  20%|██        | 103/507 [00:04<00:11, 35.24it/s]
Loading 0:  21%|██        | 107/507 [00:05<00:16, 24.45it/s]
Loading 0:  22%|██▏       | 112/507 [00:05<00:13, 28.48it/s]
Loading 0:  23%|██▎       | 116/507 [00:05<00:13, 29.23it/s]
Loading 0:  24%|██▍       | 121/507 [00:05<00:12, 31.89it/s]
Loading 0:  25%|██▍       | 125/507 [00:05<00:12, 31.34it/s]
Loading 0:  26%|██▌       | 130/507 [00:05<00:11, 33.91it/s]
Loading 0:  26%|██▋       | 134/507 [00:05<00:11, 32.83it/s]
Loading 0:  27%|██▋       | 139/507 [00:06<00:10, 34.96it/s]
Loading 0:  28%|██▊       | 143/507 [00:06<00:10, 33.56it/s]
Loading 0:  29%|██▉       | 148/507 [00:06<00:09, 36.35it/s]
Loading 0:  30%|██▉       | 152/507 [00:06<00:09, 35.70it/s]
Loading 0:  31%|███       | 157/507 [00:06<00:09, 37.30it/s]
Loading 0:  32%|███▏      | 161/507 [00:06<00:09, 36.17it/s]
Loading 0:  33%|███▎      | 165/507 [00:06<00:12, 26.57it/s]
Loading 0:  33%|███▎      | 169/507 [00:07<00:12, 26.56it/s]
Loading 0:  35%|███▍      | 175/507 [00:07<00:10, 31.48it/s]
Loading 0:  35%|███▌      | 179/507 [00:07<00:10, 32.13it/s]
Loading 0:  36%|███▋      | 184/507 [00:07<00:09, 35.17it/s]
Loading 0:  37%|███▋      | 188/507 [00:07<00:09, 35.01it/s]
Loading 0:  38%|███▊      | 193/507 [00:07<00:08, 36.57it/s]
Loading 0:  39%|███▉      | 197/507 [00:07<00:08, 34.94it/s]
Loading 0:  40%|███▉      | 202/507 [00:07<00:08, 37.53it/s]
Loading 0:  41%|████      | 206/507 [00:08<00:08, 36.71it/s]
Loading 0:  42%|████▏     | 211/507 [00:08<00:07, 38.05it/s]
Loading 0:  42%|████▏     | 215/507 [00:08<00:08, 36.17it/s]
Loading 0:  43%|████▎     | 220/507 [00:08<00:07, 38.13it/s]
Loading 0:  44%|████▍     | 224/507 [00:08<00:11, 25.12it/s]
Loading 0:  45%|████▍     | 228/507 [00:08<00:10, 27.83it/s]
Loading 0:  46%|████▌     | 232/507 [00:08<00:10, 25.89it/s]
Loading 0:  47%|████▋     | 236/507 [00:09<00:09, 28.18it/s]
Loading 0:  47%|████▋     | 240/507 [00:09<00:10, 25.82it/s]
Loading 0:  48%|████▊     | 245/507 [00:09<00:08, 29.93it/s]
Loading 0:  49%|████▉     | 249/507 [00:09<00:09, 28.19it/s]
Loading 0:  50%|█████     | 256/507 [00:09<00:07, 35.45it/s]
Loading 0:  51%|█████▏    | 260/507 [00:09<00:07, 34.44it/s]
Loading 0:  52%|█████▏    | 265/507 [00:09<00:06, 36.26it/s]
Loading 0:  53%|█████▎    | 269/507 [00:10<00:06, 34.38it/s]
Loading 0:  54%|█████▍    | 274/507 [00:10<00:06, 36.00it/s]
Loading 0:  55%|█████▍    | 278/507 [00:10<00:09, 23.81it/s]
Loading 0:  56%|█████▌    | 283/507 [00:10<00:08, 26.98it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:07, 28.04it/s]
Loading 0:  58%|█████▊    | 292/507 [00:10<00:06, 31.43it/s]
Loading 0:  58%|█████▊    | 296/507 [00:25<03:37,  1.03s/it]
Loading 0:  59%|█████▉    | 299/507 [00:25<02:48,  1.23it/s]
Loading 0:  60%|█████▉    | 303/507 [00:26<01:59,  1.71it/s]
Loading 0:  61%|██████    | 310/507 [00:26<01:07,  2.92it/s]
Loading 0:  62%|██████▏   | 314/507 [00:26<00:50,  3.83it/s]
Loading 0:  63%|██████▎   | 319/507 [00:26<00:34,  5.38it/s]
Loading 0:  64%|██████▎   | 323/507 [00:26<00:26,  6.92it/s]
Loading 0:  65%|██████▍   | 328/507 [00:26<00:18,  9.45it/s]
Loading 0:  65%|██████▌   | 332/507 [00:26<00:14, 11.71it/s]
Loading 0:  66%|██████▋   | 336/507 [00:27<00:13, 12.70it/s]
Loading 0:  67%|██████▋   | 340/507 [00:27<00:11, 14.81it/s]
Loading 0:  68%|██████▊   | 346/507 [00:27<00:08, 20.12it/s]
Loading 0:  69%|██████▉   | 350/507 [00:27<00:07, 22.26it/s]
Loading 0:  70%|███████   | 355/507 [00:27<00:05, 26.22it/s]
Loading 0:  71%|███████   | 359/507 [00:27<00:05, 27.79it/s]
Loading 0:  72%|███████▏  | 364/507 [00:27<00:04, 31.46it/s]
Loading 0:  73%|███████▎  | 368/507 [00:27<00:04, 32.37it/s]
Loading 0:  74%|███████▎  | 373/507 [00:28<00:03, 35.44it/s]
Loading 0:  74%|███████▍  | 377/507 [00:28<00:03, 35.26it/s]
Loading 0:  75%|███████▌  | 382/507 [00:28<00:03, 37.64it/s]
Loading 0:  76%|███████▌  | 386/507 [00:28<00:03, 36.05it/s]
Loading 0:  77%|███████▋  | 391/507 [00:28<00:03, 36.84it/s]
Loading 0:  78%|███████▊  | 395/507 [00:28<00:04, 25.49it/s]
Loading 0:  79%|███████▉  | 400/507 [00:28<00:03, 29.48it/s]
Loading 0:  80%|███████▉  | 404/507 [00:29<00:03, 30.62it/s]
Loading 0:  81%|████████  | 409/507 [00:29<00:02, 33.65it/s]
Loading 0:  81%|████████▏ | 413/507 [00:29<00:02, 34.08it/s]
Loading 0:  82%|████████▏ | 418/507 [00:29<00:02, 36.36it/s]
Loading 0:  83%|████████▎ | 422/507 [00:29<00:02, 35.48it/s]
Loading 0:  84%|████████▍ | 426/507 [00:29<00:02, 35.83it/s]
Loading 0:  85%|████████▍ | 430/507 [00:29<00:02, 31.40it/s]
Loading 0:  86%|████████▌ | 436/507 [00:29<00:01, 35.94it/s]
Loading 0:  87%|████████▋ | 440/507 [00:30<00:01, 34.38it/s]
Loading 0:  88%|████████▊ | 445/507 [00:30<00:01, 35.58it/s]
Loading 0:  89%|████████▊ | 449/507 [00:30<00:02, 24.98it/s]
Loading 0:  90%|████████▉ | 454/507 [00:30<00:01, 28.27it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:01, 29.17it/s]
Loading 0:  91%|█████████▏| 463/507 [00:30<00:01, 32.24it/s]
Loading 0:  92%|█████████▏| 467/507 [00:31<00:01, 32.35it/s]
Loading 0:  93%|█████████▎| 472/507 [00:31<00:00, 35.08it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:00, 34.94it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:00, 37.21it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 36.00it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 37.70it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 36.16it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 37.47it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 35.85it/s]
Loading 0: 100%|██████████| 507/507 [00:32<00:00, 24.50it/s]
                                                            
Job chaiml-nemo-small-merge-7220-v1-mkmlizer completed after 165.25s with status: succeeded
Stopping job with name chaiml-nemo-small-merge-7220-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-small-merge-7220-v1
Waiting for inference service chaiml-nemo-small-merge-7220-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-small-merge-7220-v1 ready after 130.63064455986023s
Pipeline stage MKMLDeployer completed in 131.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.788851022720337s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.281921148300171s
Received healthy response to inference request in 2.8909811973571777s
Received healthy response to inference request in 2.4643821716308594s
Received healthy response to inference request in 2.615957736968994s
5 requests
0 failed requests
5th percentile: 2.3184133529663087
10th percentile: 2.3549055576324465
20th percentile: 2.4278899669647216
30th percentile: 2.4946972846984865
40th percentile: 2.5553275108337403
50th percentile: 2.615957736968994
60th percentile: 2.6851150512695314
70th percentile: 2.7542723655700683
80th percentile: 2.809277057647705
90th percentile: 2.8501291275024414
95th percentile: 2.8705551624298096
99th percentile: 2.886895990371704
mean time: 2.608418655395508
Pipeline stage StressChecker completed in 14.24s
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 2.15s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.08s
Shutdown handler de-registered
chaiml-nemo-small-merge-_7220_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 3809.51s
Shutdown handler de-registered
chaiml-nemo-small-merge-_7220_v1 status is now inactive due to auto deactivation removed underperforming models