chaiml-1-5-k-payload-lex_6849

developer_uid: azuruce

submission_id: chaiml-1-5-k-payload-lex_6849_v1

model_name: anthropic_rank_top

model_group: ChaiML/1_5_k_payload_lex

status: inactive

timestamp: 2024-11-21T20:54:22+00:00

num_battles: 16257

num_wins: 7540

celo_rating: 1222.8

family_friendly_score: 0.5736

family_friendly_standard_error: 0.006994040892073766

submission_type: basic

model_repo: ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3848304126618651, 'latency_mean': 2.5984472703933714, 'latency_p50': 2.6206551790237427, 'latency_p90': 2.864473795890808}, {'batch_size': 3, 'throughput': 0.8245515408063618, 'latency_mean': 3.6235682344436646, 'latency_p50': 3.5959712266921997, 'latency_p90': 3.993200373649597}, {'batch_size': 5, 'throughput': 1.0984853754580304, 'latency_mean': 4.523139547109604, 'latency_p50': 4.528829097747803, 'latency_p90': 5.119352412223816}, {'batch_size': 6, 'throughput': 1.1867346327727057, 'latency_mean': 5.024227147102356, 'latency_p50': 5.01712429523468, 'latency_p90': 5.63351457118988}, {'batch_size': 10, 'throughput': 1.4097425455551973, 'latency_mean': 7.016214116811752, 'latency_p50': 6.94794237613678, 'latency_p90': 7.947088241577148}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: anthropic_rank_top

is_internal_developer: True

language_model: ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0

model_size: 22B

ranking_group: single

throughput_3p7s: 0.86

us_pacific_date: 2024-11-21

win_ratio: 0.4638002091406779

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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-1-5-k-payload-lex-6849-v1-mkmlizer
Waiting for job on chaiml-1-5-k-payload-lex-6849-v1-mkmlizer to finish
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║       /___/                                                         ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: Downloaded to shared memory in 93.326s
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptd54qy76, device:0
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: quantized model in 42.813s
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: Processed model ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0 in 136.140s
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-6849-v1
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-6849-v1/tokenizer_config.json
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-6849-v1/tokenizer.json
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-6849-v1/flywheel_model.1.safetensors
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-6849-v1/flywheel_model.0.safetensors
chaiml-1-5-k-payload-lex-6849-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.82it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 39.78it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.57it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 40.66it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.83it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 33.99it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 41.42it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.79it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 34.66it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.40it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:17, 25.58it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.98it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:13, 31.46it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 33.94it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 35.39it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.67it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.93it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.74it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 38.42it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:10, 38.58it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:10, 36.24it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:14, 27.15it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 26.77it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 27.96it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.24it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.22it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 36.68it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.96it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 37.35it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 35.62it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.47it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 37.37it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 37.85it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:11, 29.59it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 30.03it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.50it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.14it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 33.86it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 37.61it/s]
Loading 0:  39%|███▉      | 198/507 [00:05<00:07, 39.94it/s]
Loading 0:  40%|████      | 203/507 [00:05<00:08, 34.84it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:06, 42.75it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:06, 42.15it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:07, 37.17it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:09, 29.16it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 30.31it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 36.36it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 35.52it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:06, 37.41it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.11it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.62it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.31it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 39.10it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 37.57it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:05, 39.74it/s]
Loading 0:  55%|█████▍    | 278/507 [00:07<00:06, 37.16it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 34.55it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 23.99it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.37it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.37it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:45,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:23,  1.42it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.06it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.56it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<00:59,  3.26it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:38,  4.88it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.52it/s]
Loading 0:  65%|██████▍   | 328/507 [00:23<00:18,  9.75it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:14, 12.19it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:10, 16.06it/s]
Loading 0:  67%|██████▋   | 342/507 [00:24<00:10, 15.33it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:08, 17.95it/s]
Loading 0:  69%|██████▉   | 352/507 [00:24<00:07, 21.97it/s]
Loading 0:  70%|███████   | 356/507 [00:24<00:06, 22.90it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.12it/s]
Loading 0:  73%|███████▎  | 368/507 [00:25<00:04, 31.79it/s]
Loading 0:  74%|███████▎  | 373/507 [00:25<00:03, 33.95it/s]
Loading 0:  75%|███████▍  | 378/507 [00:25<00:03, 36.73it/s]
Loading 0:  76%|███████▌  | 383/507 [00:25<00:03, 32.19it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:03, 37.69it/s]
Loading 0:  78%|███████▊  | 394/507 [00:25<00:03, 34.05it/s]
Loading 0:  79%|███████▊  | 398/507 [00:26<00:03, 29.46it/s]
Loading 0:  79%|███████▉  | 402/507 [00:26<00:03, 28.56it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.78it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.78it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.12it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 35.03it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 38.00it/s]
Loading 0:  85%|████████▍ | 430/507 [00:26<00:02, 36.07it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.92it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.73it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 38.99it/s]
Loading 0:  88%|████████▊ | 448/507 [00:27<00:01, 36.79it/s]
Loading 0:  89%|████████▉ | 453/507 [00:27<00:01, 39.57it/s]
Loading 0:  90%|█████████ | 458/507 [00:29<00:07,  6.16it/s]
Loading 0:  91%|█████████ | 461/507 [00:29<00:06,  7.37it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.36it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.42it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 17.03it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.10it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 23.26it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.41it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 29.07it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 32.76it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 31.25it/s]
                                                            
Job chaiml-1-5-k-payload-lex-6849-v1-mkmlizer completed after 166.39s with status: succeeded
Stopping job with name chaiml-1-5-k-payload-lex-6849-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.90s
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-1-5-k-payload-lex-6849-v1
Waiting for inference service chaiml-1-5-k-payload-lex-6849-v1 to be ready
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: ('http://chaiml-nemo-20241010-tie-5991-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52128->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-1-5-k-payload-lex-6849-v1 ready after 231.21275281906128s
Pipeline stage MKMLDeployer completed in 231.67s
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 1.6640424728393555s
Received healthy response to inference request in 1.5551822185516357s
Received healthy response to inference request in 2.279348611831665s
Received healthy response to inference request in 1.522461175918579s
5 requests
1 failed requests
5th percentile: 1.5290053844451905
10th percentile: 1.5355495929718017
20th percentile: 1.5486380100250243
30th percentile: 1.5769542694091796
40th percentile: 1.6204983711242675
50th percentile: 1.6640424728393555
60th percentile: 1.9101649284362792
70th percentile: 2.156287384033203
80th percentile: 5.847814464569095
90th percentile: 12.984746170043948
95th percentile: 16.55321202278137
99th percentile: 19.407984704971312
mean time: 5.4285424709320065
%s, retrying in %s seconds...
Received healthy response to inference request in 0.9482779502868652s
Received healthy response to inference request in 1.4290056228637695s
Received healthy response to inference request in 1.5777084827423096s
Received healthy response to inference request in 0.9809062480926514s
Received healthy response to inference request in 1.6891872882843018s
5 requests
0 failed requests
5th percentile: 0.9548036098480225
10th percentile: 0.9613292694091797
20th percentile: 0.9743805885314941
30th percentile: 1.070526123046875
40th percentile: 1.2497658729553223
50th percentile: 1.4290056228637695
60th percentile: 1.4884867668151855
70th percentile: 1.5479679107666016
80th percentile: 1.600004243850708
90th percentile: 1.6445957660675048
95th percentile: 1.6668915271759033
99th percentile: 1.684728136062622
mean time: 1.3250171184539794
Pipeline stage StressChecker completed in 36.16s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.73s
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 2.36s
Shutdown handler de-registered
chaiml-1-5-k-payload-lex_6849_v1 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1-5-k-payload-lex-6849-v1-profiler
Waiting for inference service chaiml-1-5-k-payload-lex-6849-v1-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 3299.64s
Shutdown handler de-registered
chaiml-1-5-k-payload-lex_6849_v1 status is now inactive due to auto deactivation removed underperforming models