developer_uid: Jellywibble
submission_id: chaiml-nemo-20241017-ti_8098_v12
model_name: chaiml-nemo-20241017-ti_8098_v12
model_group: ChaiML/nemo-20241017-tie
status: inactive
timestamp: 2024-11-30T18:08:39+00:00
num_battles: 12315
num_wins: 5984
celo_rating: 1254.72
family_friendly_score: 0.5973999999999999
family_friendly_standard_error: 0.006935607255316581
submission_type: basic
model_repo: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.65337076319819, 'latency_mean': 1.5304683935642243, 'latency_p50': 1.5295695066452026, 'latency_p90': 1.6920368432998658}, {'batch_size': 3, 'throughput': 1.2727303126699374, 'latency_mean': 2.349982204437256, 'latency_p50': 2.342582941055298, 'latency_p90': 2.605987882614136}, {'batch_size': 5, 'throughput': 1.5715166121049156, 'latency_mean': 3.166110066175461, 'latency_p50': 3.1703370809555054, 'latency_p90': 3.566846323013306}, {'batch_size': 6, 'throughput': 1.6725319441164317, 'latency_mean': 3.5661692786216737, 'latency_p50': 3.603599190711975, 'latency_p90': 3.960942339897156}, {'batch_size': 8, 'throughput': 1.7747721543266395, 'latency_mean': 4.476595488786697, 'latency_p50': 4.4829628467559814, 'latency_p90': 5.003410887718201}, {'batch_size': 10, 'throughput': 1.8265329987608956, 'latency_mean': 5.43492237329483, 'latency_p50': 5.4921969175338745, 'latency_p90': 6.045206046104431}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-20241017-ti_8098_v12
is_internal_developer: True
language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert
model_size: 13B
ranking_group: single
throughput_3p7s: 1.7
us_pacific_date: 2024-11-30
win_ratio: 0.48591149005278117
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', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 8, '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-nemo-20241017-ti-8098-v12-mkmlizer
Waiting for job on chaiml-nemo-20241017-ti-8098-v12-mkmlizer to finish
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-nemo-20241017-ti-8098-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: Downloaded to shared memory in 31.800s
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi3ky7wry, device:0
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: quantized model in 37.978s
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 69.778s
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v12
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v12/special_tokens_map.json
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v12/config.json
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v12/tokenizer_config.json
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v12/tokenizer.json
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v12/flywheel_model.0.safetensors
chaiml-nemo-20241017-ti-8098-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:56,  3.15s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:02,  1.18it/s]
Loading 0:   3%|▎         | 12/363 [00:06<01:58,  2.96it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:18,  4.44it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  7.98it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:30, 11.01it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:24, 13.48it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.25it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.57it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.63it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:11, 27.74it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 27.65it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:08, 35.21it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:07, 36.76it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 38.75it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:06, 40.75it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 34.48it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 42.15it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 41.43it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 41.55it/s]
Loading 0:  30%|███       | 109/363 [00:09<00:05, 42.39it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:07, 34.04it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 28.29it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:08, 29.01it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.21it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 33.11it/s]
Loading 0:  38%|███▊      | 138/363 [00:10<00:06, 34.04it/s]
Loading 0:  39%|███▉      | 142/363 [00:10<00:06, 31.67it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 37.00it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 36.02it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 39.40it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 39.78it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 40.73it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 43.00it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:05, 35.73it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 41.78it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 41.01it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 41.03it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 42.25it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 23.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 30.54it/s]
Loading 0:  60%|█████▉    | 216/363 [00:12<00:04, 32.65it/s]
Loading 0:  61%|██████    | 221/363 [00:12<00:04, 35.07it/s]
Loading 0:  62%|██████▏   | 226/363 [00:12<00:03, 38.21it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:03, 33.84it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 39.80it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 40.43it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 41.49it/s]
Loading 0:  70%|██████▉   | 253/363 [00:13<00:02, 43.44it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:02, 35.83it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 43.40it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 42.80it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 41.68it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 43.20it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:03, 25.39it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 32.01it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 34.54it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 37.08it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 37.95it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:01, 37.92it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 42.96it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 43.31it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:00, 43.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:15<00:00, 42.02it/s]
Loading 0:  94%|█████████▎| 340/363 [00:15<00:00, 39.42it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 43.26it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 41.35it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 40.21it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 40.86it/s]
                                                            

Job chaiml-nemo-20241017-ti-8098-v12-mkmlizer completed after 94.16s with status: succeeded
Stopping job with name chaiml-nemo-20241017-ti-8098-v12-mkmlizer
Pipeline stage MKMLizer completed in 94.64s
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-nemo-20241017-ti-8098-v12
Waiting for inference service chaiml-nemo-20241017-ti-8098-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
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-nemo-20241017-ti-8098-v12 ready after 140.71630120277405s
Pipeline stage MKMLDeployer completed in 141.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0556387901306152s
Received healthy response to inference request in 1.6621074676513672s
Received healthy response to inference request in 1.4722909927368164s
Received healthy response to inference request in 1.5214722156524658s
Received healthy response to inference request in 1.6637051105499268s
5 requests
0 failed requests
5th percentile: 1.4821272373199463
10th percentile: 1.4919634819030763
20th percentile: 1.511635971069336
30th percentile: 1.5495992660522462
40th percentile: 1.6058533668518067
50th percentile: 1.6621074676513672
60th percentile: 1.662746524810791
70th percentile: 1.6633855819702148
80th percentile: 1.7420918464660646
90th percentile: 1.89886531829834
95th percentile: 1.9772520542144774
99th percentile: 2.0399614429473876
mean time: 1.6750429153442383
Pipeline stage StressChecker completed in 9.98s
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 2.41s
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 2.35s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_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 2995.41s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v12 status is now inactive due to auto deactivation removed underperforming models