chaiml-small-anthropic-r_5918

developer_uid: azuruce

submission_id: chaiml-small-anthropic-r_5918_v1

model_name: anthropic1000

model_group: ChaiML/small_anthropic_r

status: inactive

timestamp: 2024-11-19T22:06:54+00:00

num_battles: 11430

num_wins: 5899

celo_rating: 1264.62

family_friendly_score: 0.5856

family_friendly_standard_error: 0.006966672663474293

submission_type: basic

model_repo: ChaiML/small_anthropic_rerun_sample1000

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38944466701204455, 'latency_mean': 2.5676816761493684, 'latency_p50': 2.574012041091919, 'latency_p90': 2.8482457876205443}, {'batch_size': 3, 'throughput': 0.8213203941993409, 'latency_mean': 3.637687783241272, 'latency_p50': 3.6237488985061646, 'latency_p90': 4.011459231376648}, {'batch_size': 5, 'throughput': 1.0853577357926791, 'latency_mean': 4.581806272268295, 'latency_p50': 4.593726992607117, 'latency_p90': 5.042155337333679}, {'batch_size': 6, 'throughput': 1.178018620967493, 'latency_mean': 5.065214984416961, 'latency_p50': 5.07917058467865, 'latency_p90': 5.764701175689697}, {'batch_size': 10, 'throughput': 1.3882598895632252, 'latency_mean': 7.145310643911362, 'latency_p50': 7.1635202169418335, 'latency_p90': 8.007587051391601}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: anthropic1000

is_internal_developer: True

language_model: ChaiML/small_anthropic_rerun_sample1000

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-11-19

win_ratio: 0.516097987751531

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-small-anthropic-r-5918-v1-mkmlizer
Waiting for job on chaiml-small-anthropic-r-5918-v1-mkmlizer to finish
chaiml-small-anthropic-r-5918-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-anthropic-r-5918-v1-mkmlizer: ║                                                                     ║
chaiml-small-anthropic-r-5918-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-anthropic-r-5918-v1-mkmlizer: Downloaded to shared memory in 92.376s
chaiml-small-anthropic-r-5918-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfi8sbtli, device:0
chaiml-small-anthropic-r-5918-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-anthropic-r-5918-v1-mkmlizer: quantized model in 43.238s
chaiml-small-anthropic-r-5918-v1-mkmlizer: Processed model ChaiML/small_anthropic_rerun_sample1000 in 135.614s
chaiml-small-anthropic-r-5918-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-anthropic-r-5918-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-anthropic-r-5918-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1
chaiml-small-anthropic-r-5918-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1/special_tokens_map.json
chaiml-small-anthropic-r-5918-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1/config.json
chaiml-small-anthropic-r-5918-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1/tokenizer_config.json
chaiml-small-anthropic-r-5918-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-anthropic-r-5918-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1/flywheel_model.1.safetensors
chaiml-small-anthropic-r-5918-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-anthropic-r-5918-v1/flywheel_model.0.safetensors
chaiml-small-anthropic-r-5918-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.20it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 41.05it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.48it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.14it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 41.20it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 35.29it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 42.99it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 42.78it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 36.33it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.43it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 27.01it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.45it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 33.21it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 36.10it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 38.02it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:10, 40.01it/s]
Loading 0:  18%|█▊        | 90/507 [00:02<00:11, 37.07it/s]
Loading 0:  19%|█▊        | 94/507 [00:02<00:10, 37.71it/s]
Loading 0:  19%|█▉        | 98/507 [00:02<00:11, 34.47it/s]
Loading 0:  21%|██        | 105/507 [00:02<00:09, 41.63it/s]
Loading 0:  22%|██▏       | 110/507 [00:02<00:09, 40.24it/s]
Loading 0:  23%|██▎       | 115/507 [00:03<00:13, 29.39it/s]
Loading 0:  23%|██▎       | 119/507 [00:03<00:12, 30.59it/s]
Loading 0:  24%|██▍       | 123/507 [00:03<00:12, 29.92it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:11, 31.71it/s]
Loading 0:  26%|██▌       | 131/507 [00:03<00:12, 29.11it/s]
Loading 0:  27%|██▋       | 136/507 [00:03<00:10, 33.75it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:11, 31.48it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 39.71it/s]
Loading 0:  30%|██▉       | 152/507 [00:04<00:09, 39.24it/s]
Loading 0:  31%|███       | 157/507 [00:04<00:08, 39.93it/s]
Loading 0:  32%|███▏      | 162/507 [00:04<00:08, 41.76it/s]
Loading 0:  33%|███▎      | 167/507 [00:04<00:08, 41.89it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 25.31it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:13, 25.26it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:10, 32.38it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 32.13it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:09, 34.89it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:09, 33.55it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 35.59it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:09, 33.53it/s]
Loading 0:  41%|████      | 209/507 [00:06<00:08, 34.99it/s]
Loading 0:  42%|████▏     | 213/507 [00:06<00:09, 30.76it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 32.92it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:09, 31.64it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:11, 24.12it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:11, 24.35it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 31.74it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.35it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 33.87it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 32.71it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 34.21it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 33.32it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 36.27it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 35.06it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 37.28it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 35.50it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 37.04it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 25.06it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.96it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.96it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:46,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:24,  1.42it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.04it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.53it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<01:00,  3.22it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:39,  4.84it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:28,  6.45it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:19,  9.16it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.42it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 14.15it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.88it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.50it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:07, 20.32it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 26.64it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 28.34it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 32.64it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 33.18it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.41it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 35.44it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 38.70it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 39.50it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 35.72it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:03, 28.20it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 29.75it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 36.33it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 35.59it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 38.05it/s]
Loading 0:  83%|████████▎ | 422/507 [00:27<00:02, 38.08it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.83it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 34.57it/s]
Loading 0:  86%|████████▌ | 434/507 [00:27<00:02, 35.48it/s]
Loading 0:  86%|████████▋ | 438/507 [00:27<00:02, 31.37it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 35.84it/s]
Loading 0:  88%|████████▊ | 448/507 [00:27<00:01, 34.83it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 37.20it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:07,  6.16it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.35it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.40it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.56it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 17.15it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.44it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 23.96it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 28.32it/s]
Loading 0:  98%|█████████▊| 495/507 [00:31<00:00, 31.19it/s]
Loading 0:  99%|█████████▊| 500/507 [00:31<00:00, 33.60it/s]
Loading 0: 100%|█████████▉| 505/507 [00:31<00:00, 36.50it/s]
                                                            
Job chaiml-small-anthropic-r-5918-v1-mkmlizer completed after 168.28s with status: succeeded
Stopping job with name chaiml-small-anthropic-r-5918-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.93s
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-small-anthropic-r-5918-v1
Waiting for inference service chaiml-small-anthropic-r-5918-v1 to be ready
Retrying (%r) after connection broken by '%r': %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
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-r-5918-v1 ready after 212.28866720199585s
Pipeline stage MKMLDeployer completed in 212.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.871213674545288s
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
Received healthy response to inference request in 2.434098958969116s
Received healthy response to inference request in 2.4347639083862305s
Received healthy response to inference request in 2.4114763736724854s
Received healthy response to inference request in 2.589510440826416s
5 requests
0 failed requests
5th percentile: 2.4160008907318113
10th percentile: 2.420525407791138
20th percentile: 2.42957444190979
30th percentile: 2.4342319488525392
40th percentile: 2.434497928619385
50th percentile: 2.4347639083862305
60th percentile: 2.4966625213623046
70th percentile: 2.5585611343383787
80th percentile: 2.6458510875701906
90th percentile: 2.7585323810577393
95th percentile: 2.8148730278015135
99th percentile: 2.859945545196533
mean time: 2.548212671279907
Pipeline stage StressChecker completed in 14.58s
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 3.04s
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 3.55s
Shutdown handler de-registered
chaiml-small-anthropic-r_5918_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 3106.86s
Shutdown handler de-registered
chaiml-small-anthropic-r_5918_v1 status is now inactive due to auto deactivation removed underperforming models