chaiml-small-anthropic-_1700

developer_uid: zonemercy

submission_id: chaiml-small-anthropic-_1700_v12

model_name: chaiml-small-anthropic-_1700_v12

model_group: ChaiML/small_anthropic_a

status: inactive

timestamp: 2024-12-03T10:28:10+00:00

num_battles: 11638

num_wins: 5674

celo_rating: 1255.83

family_friendly_score: 0.5900000000000001

family_friendly_standard_error: 0.0069555733049116815

submission_type: basic

model_repo: ChaiML/small_anthropic_addict_lexical_1120

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38378630874837655, 'latency_mean': 2.605554219484329, 'latency_p50': 2.616890072822571, 'latency_p90': 2.8651084899902344}, {'batch_size': 3, 'throughput': 0.8229307323658819, 'latency_mean': 3.6287883913516996, 'latency_p50': 3.635207176208496, 'latency_p90': 3.976032447814941}, {'batch_size': 5, 'throughput': 1.0946054251326056, 'latency_mean': 4.541605974435806, 'latency_p50': 4.535444378852844, 'latency_p90': 5.029812574386597}, {'batch_size': 6, 'throughput': 1.172500416757486, 'latency_mean': 5.096399807929993, 'latency_p50': 5.122018098831177, 'latency_p90': 5.649592924118042}, {'batch_size': 10, 'throughput': 1.3968414614894193, 'latency_mean': 7.098720302581787, 'latency_p50': 7.09958279132843, 'latency_p90': 8.013496685028077}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-anthropic-_1700_v12

is_internal_developer: True

language_model: ChaiML/small_anthropic_addict_lexical_1120

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-12-03

win_ratio: 0.4875408145729507

generation_params: {'temperature': 1.0, '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': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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-anthropic-1700-v12-mkmlizer
Waiting for job on chaiml-small-anthropic-1700-v12-mkmlizer to finish
chaiml-small-anthropic-1700-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-anthropic-1700-v12-mkmlizer: ║     _____            __           __                                ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║       /___/                                                         ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-anthropic-1700-v12-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-1700-v12-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-small-anthropic-1700-v12-mkmlizer: Downloaded to shared memory in 75.420s
chaiml-small-anthropic-1700-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjschon37, device:0
chaiml-small-anthropic-1700-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-anthropic-1700-v12-mkmlizer: quantized model in 43.844s
chaiml-small-anthropic-1700-v12-mkmlizer: Processed model ChaiML/small_anthropic_addict_lexical_1120 in 119.264s
chaiml-small-anthropic-1700-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-anthropic-1700-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-anthropic-1700-v12/config.json
chaiml-small-anthropic-1700-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-anthropic-1700-v12/special_tokens_map.json
chaiml-small-anthropic-1700-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-anthropic-1700-v12/tokenizer_config.json
chaiml-small-anthropic-1700-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-anthropic-1700-v12/tokenizer.json
chaiml-small-anthropic-1700-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-1700-v12/flywheel_model.1.safetensors
chaiml-small-anthropic-1700-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-1700-v12/flywheel_model.0.safetensors
chaiml-small-anthropic-1700-v12-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.18it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.59it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.57it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 40.49it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.29it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.05it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 41.39it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 41.25it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 35.09it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 28.24it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 26.85it/s]
Loading 0:  12%|█▏        | 61/507 [00:01<00:15, 28.70it/s]
Loading 0:  13%|█▎        | 65/507 [00:01<00:16, 27.40it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:12, 34.30it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:12, 35.58it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 33.88it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 39.66it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.87it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.24it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 37.88it/s]
Loading 0:  21%|██        | 106/507 [00:02<00:10, 38.11it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 37.76it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:14, 26.72it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:14, 26.35it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.15it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:12, 31.01it/s]
Loading 0:  26%|██▌       | 131/507 [00:03<00:12, 29.44it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:09, 37.26it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 37.44it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:09, 38.55it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:09, 38.40it/s]
Loading 0:  31%|███       | 157/507 [00:04<00:09, 35.58it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:09, 35.74it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:08, 38.42it/s]
Loading 0:  34%|███▎      | 170/507 [00:05<00:12, 27.42it/s]
Loading 0:  34%|███▍      | 174/507 [00:05<00:11, 27.97it/s]
Loading 0:  35%|███▌      | 178/507 [00:05<00:11, 28.22it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:10, 31.69it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:10, 31.98it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 35.09it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 34.70it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:07, 38.42it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:07, 38.20it/s]
Loading 0:  42%|████▏     | 211/507 [00:06<00:07, 41.16it/s]
Loading 0:  43%|████▎     | 217/507 [00:06<00:07, 40.96it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:07, 38.49it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:09, 29.39it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 28.15it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 35.25it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 34.67it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 37.02it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.83it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.96it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.77it/s]
Loading 0:  52%|█████▏    | 263/507 [00:07<00:06, 36.51it/s]
Loading 0:  53%|█████▎    | 267/507 [00:07<00:07, 32.29it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 37.23it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 33.86it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 35.30it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 24.17it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 26.77it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 26.77it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:47,  1.24it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:26,  1.40it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:38,  2.02it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:18,  2.51it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:55,  3.45it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.03it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.12it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.14it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.63it/s]
Loading 0:  66%|██████▋   | 336/507 [00:24<00:11, 14.48it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.21it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:09, 18.04it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:07, 20.14it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 26.47it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 28.28it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 32.79it/s]
Loading 0:  73%|███████▎  | 368/507 [00:25<00:04, 34.48it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.27it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.32it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 36.88it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 36.79it/s]
Loading 0:  77%|███████▋  | 390/507 [00:26<00:03, 33.61it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:03, 28.45it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 29.68it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 35.87it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 35.26it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.23it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 34.71it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.19it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 36.40it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 39.72it/s]
Loading 0:  87%|████████▋ | 440/507 [00:27<00:01, 40.36it/s]
Loading 0:  88%|████████▊ | 445/507 [00:27<00:01, 40.63it/s]
Loading 0:  89%|████████▉ | 450/507 [00:27<00:01, 42.31it/s]
Loading 0:  90%|████████▉ | 455/507 [00:30<00:08,  6.35it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  7.87it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:03, 10.99it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 15.77it/s]
Loading 0:  94%|█████████▍| 477/507 [00:30<00:01, 18.83it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.41it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 22.86it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 25.84it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 26.65it/s]
Loading 0:  98%|█████████▊| 498/507 [00:31<00:00, 29.31it/s]
Loading 0:  99%|█████████▉| 502/507 [00:31<00:00, 27.42it/s]
                                                            
Job chaiml-small-anthropic-1700-v12-mkmlizer completed after 155.91s with status: succeeded
Stopping job with name chaiml-small-anthropic-1700-v12-mkmlizer
Pipeline stage MKMLizer completed in 156.40s
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-anthropic-1700-v12
Waiting for inference service chaiml-small-anthropic-1700-v12 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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-small-anthropic-1700-v12 ready after 150.64441919326782s
Pipeline stage MKMLDeployer completed in 151.16s
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 2.771848678588867s
Received healthy response to inference request in 2.5950794219970703s
Received healthy response to inference request in 2.313675880432129s
Received healthy response to inference request in 2.3055434226989746s
5 requests
1 failed requests
Connection pool is full, discarding connection: %s. Connection pool size: %s
5th percentile: 2.3071699142456055
Connection pool is full, discarding connection: %s. Connection pool size: %s
10th percentile: 2.3087964057922363
20th percentile: 2.312049388885498
30th percentile: 2.3699565887451173
40th percentile: 2.4825180053710936
50th percentile: 2.5950794219970703
60th percentile: 2.665787124633789
70th percentile: 2.7364948272705076
80th percentile: 6.244757795333865
90th percentile: 13.190576028823855
95th percentile: 16.663485145568846
99th percentile: 19.441812438964842
mean time: 6.024508333206176
%s, retrying in %s seconds...
Received healthy response to inference request in 2.2898714542388916s
Received healthy response to inference request in 2.9577338695526123s
Received healthy response to inference request in 2.3230350017547607s
Received healthy response to inference request in 2.8333065509796143s
Received healthy response to inference request in 2.4599969387054443s
5 requests
0 failed requests
5th percentile: 2.2965041637420653
10th percentile: 2.303136873245239
20th percentile: 2.316402292251587
30th percentile: 2.3504273891448975
40th percentile: 2.405212163925171
50th percentile: 2.4599969387054443
60th percentile: 2.609320783615112
70th percentile: 2.75864462852478
80th percentile: 2.8581920146942137
90th percentile: 2.907962942123413
95th percentile: 2.932848405838013
99th percentile: 2.9527567768096925
mean time: 2.5727887630462645
Pipeline stage StressChecker completed in 45.72s
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 2.14s
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 2.10s
Shutdown handler de-registered
chaiml-small-anthropic-_1700_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 3616.50s
Shutdown handler de-registered
chaiml-small-anthropic-_1700_v12 status is now inactive due to auto deactivation removed underperforming models