developer_uid: rirv938
submission_id: chaiml-nemo-anthropic-_38239_v10
model_name: chaiml-nemo-anthropic-_38239_v10
model_group: ChaiML/nemo_anthropic_ad
status: torndown
timestamp: 2024-12-31T06:38:20+00:00
num_battles: 16615
num_wins: 8401
celo_rating: 1266.74
family_friendly_score: 0.5913999999999999
family_friendly_standard_error: 0.006951921173316049
submission_type: basic
model_repo: ChaiML/nemo_anthropic_addict_lexical_1120_run2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6347267745856874, 'latency_mean': 1.5753851282596587, 'latency_p50': 1.5712625980377197, 'latency_p90': 1.7605107069015502}, {'batch_size': 3, 'throughput': 1.2661337967010933, 'latency_mean': 2.3619008147716523, 'latency_p50': 2.358890652656555, 'latency_p90': 2.614494204521179}, {'batch_size': 5, 'throughput': 1.5823588841569514, 'latency_mean': 3.143524650335312, 'latency_p50': 3.172038435935974, 'latency_p90': 3.542043447494507}, {'batch_size': 6, 'throughput': 1.7059633802088792, 'latency_mean': 3.500071371793747, 'latency_p50': 3.5151844024658203, 'latency_p90': 3.8827232122421265}, {'batch_size': 8, 'throughput': 1.8371530001354857, 'latency_mean': 4.320789750814438, 'latency_p50': 4.334550142288208, 'latency_p90': 4.842729544639587}, {'batch_size': 10, 'throughput': 1.9310692187194807, 'latency_mean': 5.140160199403763, 'latency_p50': 5.17245614528656, 'latency_p90': 5.754912948608398}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-anthropic-_38239_v10
is_internal_developer: True
language_model: ChaiML/nemo_anthropic_addict_lexical_1120_run2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.75
us_pacific_date: 2024-12-30
win_ratio: 0.5056274450797472
generation_params: {'temperature': 1.0, '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-anthropic-38239-v10-mkmlizer
Waiting for job on chaiml-nemo-anthropic-38239-v10-mkmlizer to finish
chaiml-nemo-anthropic-38239-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ║                                                                     ║
chaiml-nemo-anthropic-38239-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-anthropic-38239-v10-mkmlizer: Downloaded to shared memory in 42.018s
chaiml-nemo-anthropic-38239-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvrfoirlu, device:0
chaiml-nemo-anthropic-38239-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-anthropic-38239-v10-mkmlizer: quantized model in 38.420s
chaiml-nemo-anthropic-38239-v10-mkmlizer: Processed model ChaiML/nemo_anthropic_addict_lexical_1120_run2 in 80.438s
chaiml-nemo-anthropic-38239-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-anthropic-38239-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-anthropic-38239-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-anthropic-38239-v10
chaiml-nemo-anthropic-38239-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-38239-v10/config.json
chaiml-nemo-anthropic-38239-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-38239-v10/special_tokens_map.json
chaiml-nemo-anthropic-38239-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-38239-v10/tokenizer_config.json
chaiml-nemo-anthropic-38239-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-38239-v10/tokenizer.json
chaiml-nemo-anthropic-38239-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-anthropic-38239-v10/flywheel_model.0.safetensors
chaiml-nemo-anthropic-38239-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.53it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.48it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.25it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.67it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.04it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.54it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 48.74it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.69it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.52it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.25it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.37it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.51it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 38.71it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.86it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 44.69it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:10, 25.94it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:08, 29.93it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:07, 33.29it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:07, 35.39it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.01it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 36.11it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.38it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 36.23it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:08, 27.11it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 28.09it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 26.83it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 29.62it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 28.48it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:06, 32.52it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:06, 31.62it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 40.59it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 39.69it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 38.28it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 37.65it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.48it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:04, 39.96it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:05, 31.68it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 39.76it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.30it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 38.91it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 24.20it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 26.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.29it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 34.76it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 35.75it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 37.33it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 30.52it/s]
Loading 0:  72%|███████▏  | 262/363 [00:07<00:02, 33.81it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:03, 31.80it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.23it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 38.05it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:02, 38.04it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:02, 36.80it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:02, 35.48it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:02, 33.25it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 32.37it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:28,  2.07it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.81it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  6.18it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.74it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:03, 10.46it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:02, 12.80it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 16.72it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:01, 20.10it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 22.85it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 24.51it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 29.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 29.40it/s]
                                                            

Job chaiml-nemo-anthropic-38239-v10-mkmlizer completed after 126.21s with status: succeeded
Stopping job with name chaiml-nemo-anthropic-38239-v10-mkmlizer
Pipeline stage MKMLizer completed in 126.68s
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-nemo-anthropic-38239-v10
Waiting for inference service chaiml-nemo-anthropic-38239-v10 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-nemo-anthropic-38239-v10 ready after 311.3273365497589s
Pipeline stage MKMLDeployer completed in 311.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9889941215515137s
Received healthy response to inference request in 1.5319809913635254s
Received healthy response to inference request in 1.5478713512420654s
Received healthy response to inference request in 1.5741536617279053s
Received healthy response to inference request in 1.5403738021850586s
5 requests
0 failed requests
5th percentile: 1.5336595535278321
10th percentile: 1.5353381156921386
20th percentile: 1.5386952400207519
30th percentile: 1.54187331199646
40th percentile: 1.5448723316192627
50th percentile: 1.5478713512420654
60th percentile: 1.5583842754364015
70th percentile: 1.5688971996307373
80th percentile: 1.657121753692627
90th percentile: 1.8230579376220704
95th percentile: 1.906026029586792
99th percentile: 1.9724005031585694
mean time: 1.6366747856140136
Pipeline stage StressChecker completed in 9.46s
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 0.75s
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 0.64s
Shutdown handler de-registered
chaiml-nemo-anthropic-_38239_v10 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 2631.95s
Shutdown handler de-registered
chaiml-nemo-anthropic-_38239_v10 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-anthropic-_38239_v10 status is now torndown due to DeploymentManager action
chaiml-nemo-anthropic-_38239_v10 status is now torndown due to DeploymentManager action
chaiml-nemo-anthropic-_38239_v10 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1