chaiml-nemo-20241017-ti_8098

developer_uid: jxlu90

submission_id: chaiml-nemo-20241017-ti_8098_v13

model_name: chaiml-nemo-20241017-ti_8098_v13

model_group: ChaiML/nemo-20241017-tie

status: inactive

timestamp: 2024-12-17T23:48:38+00:00

num_battles: 9035

num_wins: 4654

celo_rating: 1275.41

family_friendly_score: 0.5922000000000001

family_friendly_standard_error: 0.006949808054903387

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: 2048

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5035180823965674, 'latency_mean': 1.9859696841239929, 'latency_p50': 1.9872756004333496, 'latency_p90': 2.156304717063904}, {'batch_size': 2, 'throughput': 0.7018406141180338, 'latency_mean': 2.8441849505901335, 'latency_p50': 2.820910692214966, 'latency_p90': 3.156627750396728}, {'batch_size': 3, 'throughput': 0.8077637961326335, 'latency_mean': 3.7022186958789827, 'latency_p50': 3.7201677560806274, 'latency_p90': 4.023245453834534}, {'batch_size': 4, 'throughput': 0.8822701741764325, 'latency_mean': 4.519772592782974, 'latency_p50': 4.563472628593445, 'latency_p90': 5.029909920692444}, {'batch_size': 5, 'throughput': 0.9215462375864646, 'latency_mean': 5.403706443309784, 'latency_p50': 5.399500131607056, 'latency_p90': 6.173591732978821}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-nemo-20241017-ti_8098_v13

is_internal_developer: True

language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

model_size: 13B

ranking_group: single

throughput_3p7s: 0.81

us_pacific_date: 2024-12-17

win_ratio: 0.5151079136690647

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': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '{memory}\n####\n', '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-20241017-ti-8098-v13-mkmlizer
Waiting for job on chaiml-nemo-20241017-ti-8098-v13-mkmlizer to finish
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: Downloaded to shared memory in 49.943s
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv1x40p61, device:0
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: quantized model in 36.881s
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 86.824s
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v13
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v13/config.json
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v13/special_tokens_map.json
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v13/tokenizer_config.json
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v13/tokenizer.json
chaiml-nemo-20241017-ti-8098-v13-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:36,  3.09s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:57,  1.20it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.30it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:05,  5.25it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:43,  7.77it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.28it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.58it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.40it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.85it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.18it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 27.75it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 28.47it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:07, 37.07it/s]
Loading 0:  20%|██        | 74/363 [00:08<00:07, 37.35it/s]
Loading 0:  22%|██▏       | 79/363 [00:08<00:07, 37.53it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:06, 41.57it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:06, 39.73it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 40.60it/s]
Loading 0:  28%|██▊       | 100/363 [00:08<00:06, 42.19it/s]
Loading 0:  29%|██▉       | 105/363 [00:08<00:07, 35.26it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 42.35it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:05, 41.20it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:08, 29.01it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:07, 30.84it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 34.13it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:06, 36.02it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 33.68it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 41.83it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:04, 42.71it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 43.06it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:04, 42.39it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 40.68it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 44.71it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 44.43it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 45.30it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:03, 44.30it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:03, 43.31it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 32.81it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 32.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 36.20it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 36.67it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 40.85it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 42.98it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:03, 36.98it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 45.07it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 43.57it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 41.84it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 45.31it/s]
Loading 0:  72%|███████▏  | 261/363 [00:12<00:02, 44.64it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:02, 44.89it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:02, 43.54it/s]
Loading 0:  76%|███████▋  | 277/363 [00:13<00:02, 42.44it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 33.01it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 32.85it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 37.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 38.81it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 38.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:01, 42.99it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 42.29it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 42.84it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 44.18it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 36.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 44.03it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 45.43it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 37.05it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 44.30it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 44.55it/s]
                                                            
Job chaiml-nemo-20241017-ti-8098-v13-mkmlizer completed after 114.17s with status: succeeded
Stopping job with name chaiml-nemo-20241017-ti-8098-v13-mkmlizer
Pipeline stage MKMLizer completed in 114.65s
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-v13
Waiting for inference service chaiml-nemo-20241017-ti-8098-v13 to be ready
Inference service chaiml-nemo-20241017-ti-8098-v13 ready after 241.43295764923096s
Pipeline stage MKMLDeployer completed in 241.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9579989910125732s
Received healthy response to inference request in 1.4445030689239502s
Received healthy response to inference request in 1.4790277481079102s
Received healthy response to inference request in 1.5157051086425781s
Received healthy response to inference request in 1.3916785717010498s
5 requests
0 failed requests
5th percentile: 1.40224347114563
10th percentile: 1.41280837059021
20th percentile: 1.43393816947937
30th percentile: 1.4514080047607423
40th percentile: 1.4652178764343262
50th percentile: 1.4790277481079102
60th percentile: 1.4936986923217774
70th percentile: 1.5083696365356445
80th percentile: 1.6041638851165771
90th percentile: 1.7810814380645752
95th percentile: 1.8695402145385742
99th percentile: 1.9403072357177735
mean time: 1.5577826976776123
Pipeline stage StressChecker completed in 8.87s
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 2.13s
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 1.98s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v13 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 3471.89s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v13 status is now inactive due to auto deactivation removed underperforming models