chaiml-exp112-nemo12b-sf_6117

developer_uid: NischayDnk

submission_id: chaiml-exp112-nemo12b-sf_6117_v2

model_name: chaiml-exp112-nemo12b-sf_6117_v2

model_group: ChaiML/exp112-nemo12B-sf

status: torndown

timestamp: 2025-03-21T18:03:00+00:00

num_battles: 7216

num_wins: 3536

celo_rating: 1275.51

family_friendly_score: 0.5591999999999999

family_friendly_standard_error: 0.007021329788579938

submission_type: basic

model_repo: ChaiML/exp112-nemo12B-sftmix4M-e3-07s

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5946544525895637, 'latency_mean': 1.6815625631809235, 'latency_p50': 1.6788417100906372, 'latency_p90': 1.8440274238586425}, {'batch_size': 3, 'throughput': 1.079873752855686, 'latency_mean': 2.7689648246765137, 'latency_p50': 2.7763410806655884, 'latency_p90': 3.070368528366089}, {'batch_size': 5, 'throughput': 1.3071283971759153, 'latency_mean': 3.808334288597107, 'latency_p50': 3.785300850868225, 'latency_p90': 4.279140591621399}, {'batch_size': 6, 'throughput': 1.3597464794123062, 'latency_mean': 4.381618809700012, 'latency_p50': 4.419175028800964, 'latency_p90': 4.943112564086914}, {'batch_size': 8, 'throughput': 1.4082786202406818, 'latency_mean': 5.638403507471085, 'latency_p50': 5.632447838783264, 'latency_p90': 6.287336254119873}, {'batch_size': 10, 'throughput': 1.4646818139548219, 'latency_mean': 6.778704288005829, 'latency_p50': 6.7489482164382935, 'latency_p90': 7.589236187934875}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp112-nemo12b-sf_6117_v2

is_internal_developer: False

language_model: ChaiML/exp112-nemo12B-sftmix4M-e3-07s

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-03-21

win_ratio: 0.49002217294900224

generation_params: {'temperature': 1.0, 'top_p': 0.975, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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-exp112-nemo12b-sf-6117-v2-mkmlizer
Waiting for job on chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer to finish
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║                                                                     ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║                                                                     ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║                                                                     ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ║                                                                     ║
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: Downloaded to shared memory in 39.479s
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmo7f2wjz, device:0
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: quantized model in 36.527s
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: Processed model ChaiML/exp112-nemo12B-sftmix4M-e3-07s in 76.007s
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp112-nemo12b-sf-6117-v2
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp112-nemo12b-sf-6117-v2/config.json
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp112-nemo12b-sf-6117-v2/special_tokens_map.json
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp112-nemo12b-sf-6117-v2/tokenizer_config.json
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp112-nemo12b-sf-6117-v2/tokenizer.json
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp112-nemo12b-sf-6117-v2/flywheel_model.0.safetensors
chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.61it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.73it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.22it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.47it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.45it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.07it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.86it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.97it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.32it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.40it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.77it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.34it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.74it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 39.55it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 43.81it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 43.99it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 43.80it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 43.25it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.54it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.10it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 45.11it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 38.04it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.45it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 42.86it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 28.68it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 30.55it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.33it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.30it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.98it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 42.37it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.16it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 44.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 43.09it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 41.84it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 46.26it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 45.44it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 41.39it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 41.96it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 32.61it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.36it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.95it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.56it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.63it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.55it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.73it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 39.76it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.38it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.87it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.71it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 44.70it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.74it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.58it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.46it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.08it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.45it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.16it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.14it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.18it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.67it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03, 10.55it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.30it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.04it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.47it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.21it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.00it/s]
                                                            
Job chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer completed after 104.9s with status: succeeded
Stopping job with name chaiml-exp112-nemo12b-sf-6117-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.60s
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-exp112-nemo12b-sf-6117-v2
Waiting for inference service chaiml-exp112-nemo12b-sf-6117-v2 to be ready
Inference service chaiml-exp112-nemo12b-sf-6117-v2 ready after 90.42296242713928s
Pipeline stage MKMLDeployer completed in 90.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5366618633270264s
Received healthy response to inference request in 1.688316822052002s
Received healthy response to inference request in 2.0251524448394775s
Received healthy response to inference request in 1.5478601455688477s
Received healthy response to inference request in 1.5825860500335693s
5 requests
0 failed requests
5th percentile: 1.554805326461792
10th percentile: 1.5617505073547364
20th percentile: 1.575640869140625
30th percentile: 1.603732204437256
40th percentile: 1.646024513244629
50th percentile: 1.688316822052002
60th percentile: 1.8230510711669923
70th percentile: 1.9577853202819824
80th percentile: 2.1274543285369876
90th percentile: 2.3320580959320067
95th percentile: 2.4343599796295163
99th percentile: 2.516201486587524
mean time: 1.8761154651641845
Pipeline stage StressChecker completed in 10.54s
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 0.79s
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 0.69s
Shutdown handler de-registered
chaiml-exp112-nemo12b-sf_6117_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp112-nemo12b-sf-6117-v2-profiler
Waiting for inference service chaiml-exp112-nemo12b-sf-6117-v2-profiler to be ready
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 2666.45s
Shutdown handler de-registered
chaiml-exp112-nemo12b-sf_6117_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp112-nemo12b-sf_6117_v2 status is now torndown due to DeploymentManager action