chaiml-nis-exp62-ftexp6_35561

developer_uid: NischayDnk

submission_id: chaiml-nis-exp62-ftexp6_35561_v1

model_name: chaiml-nis-exp62-ftexp6_35561_v1

model_group: ChaiML/nis-exp62-ftexp61

status: torndown

timestamp: 2025-03-10T05:29:26+00:00

num_battles: 11792

num_wins: 6101

celo_rating: 1290.51

family_friendly_score: 0.5164

family_friendly_standard_error: 0.007067263119482675

submission_type: basic

model_repo: ChaiML/nis-exp62-ftexp61-DPO-6k-13B

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': 0.5879172182368506, 'latency_mean': 1.700835372209549, 'latency_p50': 1.7029798030853271, 'latency_p90': 1.8823896884918212}, {'batch_size': 3, 'throughput': 1.0677341333342514, 'latency_mean': 2.7962313532829284, 'latency_p50': 2.8136634826660156, 'latency_p90': 3.0796066522598267}, {'batch_size': 5, 'throughput': 1.2813457571564237, 'latency_mean': 3.884986499547958, 'latency_p50': 3.8755279779434204, 'latency_p90': 4.313650751113891}, {'batch_size': 6, 'throughput': 1.329120327273521, 'latency_mean': 4.494585065841675, 'latency_p50': 4.50925886631012, 'latency_p90': 4.995942950248718}, {'batch_size': 8, 'throughput': 1.409640976232798, 'latency_mean': 5.630621956586838, 'latency_p50': 5.650847911834717, 'latency_p90': 6.362377619743347}, {'batch_size': 10, 'throughput': 1.4370661657002761, 'latency_mean': 6.920540380477905, 'latency_p50': 6.936905264854431, 'latency_p90': 7.640222144126892}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-nis-exp62-ftexp6_35561_v1

is_internal_developer: False

language_model: ChaiML/nis-exp62-ftexp61-DPO-6k-13B

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-03-09

win_ratio: 0.5173846675712347

generation_params: {'temperature': 0.85, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['You:', '</s>', '###', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]', 'prompt_template': "''", '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': '[/INST]{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-nis-exp62-ftexp6-35561-v1-mkmlizer
Waiting for job on chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer to finish
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║                                                                     ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║                                                                     ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║                                                                     ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ║                                                                     ║
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: Downloaded to shared memory in 41.275s
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp38e0n9vj, device:0
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: quantized model in 35.354s
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: Processed model ChaiML/nis-exp62-ftexp61-DPO-6k-13B in 76.630s
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-exp62-ftexp6-35561-v1
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-exp62-ftexp6-35561-v1/config.json
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-exp62-ftexp6-35561-v1/special_tokens_map.json
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-exp62-ftexp6-35561-v1/tokenizer_config.json
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-exp62-ftexp6-35561-v1/tokenizer.json
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-exp62-ftexp6-35561-v1/flywheel_model.0.safetensors
chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.28it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.42it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.12it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:07, 48.14it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.62it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.34it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.48it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.72it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 49.56it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.73it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 38.22it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.66it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.68it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 43.46it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 49.10it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.72it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.07it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.55it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 49.72it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:04, 48.72it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:05, 43.27it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 50.03it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 48.51it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:06, 34.34it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 36.64it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 39.22it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 39.44it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:04, 44.20it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 43.69it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 41.93it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.45it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.65it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.45it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.40it/s]
Loading 0:  60%|█████▉    | 216/363 [00:04<00:03, 48.75it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:03, 46.32it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.74it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.64it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.15it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 38.59it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 40.51it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 40.12it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 39.78it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.29it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.92it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 40.36it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:02, 40.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 35.60it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 43.97it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 42.89it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 43.65it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:21,  2.58it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:15,  3.31it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.40it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.36it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.47it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.51it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.16it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 21.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.62it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 30.61it/s]
                                                            
Job chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer completed after 103.77s with status: succeeded
Stopping job with name chaiml-nis-exp62-ftexp6-35561-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.27s
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-nis-exp62-ftexp6-35561-v1
Waiting for inference service chaiml-nis-exp62-ftexp6-35561-v1 to be ready
Inference service chaiml-nis-exp62-ftexp6-35561-v1 ready after 90.51233458518982s
Pipeline stage MKMLDeployer completed in 91.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.093763589859009s
Received healthy response to inference request in 2.0959720611572266s
Received healthy response to inference request in 1.6343202590942383s
Received healthy response to inference request in 1.5163795948028564s
Received healthy response to inference request in 1.831367015838623s
5 requests
0 failed requests
5th percentile: 1.5399677276611328
10th percentile: 1.563555860519409
20th percentile: 1.610732126235962
30th percentile: 1.6737296104431152
40th percentile: 1.7525483131408692
50th percentile: 1.831367015838623
60th percentile: 1.9363256454467774
70th percentile: 2.041284275054932
80th percentile: 2.0942052841186523
90th percentile: 2.0950886726379396
95th percentile: 2.095530366897583
99th percentile: 2.095883722305298
mean time: 1.8343605041503905
Pipeline stage StressChecker completed in 10.67s
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 0.71s
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 0.68s
Shutdown handler de-registered
chaiml-nis-exp62-ftexp6_35561_v1 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 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nis-exp62-ftexp6-35561-v1-profiler
Waiting for inference service chaiml-nis-exp62-ftexp6-35561-v1-profiler to be ready
Inference service chaiml-nis-exp62-ftexp6-35561-v1-profiler ready after 90.36424207687378s
Pipeline stage MKMLProfilerDeployer completed in 90.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-exp62-fte0e184ca132a7d28621728471a9b52a13-deplofc5w9:/code/chaiverse_profiler_1741584906 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-exp62-fte0e184ca132a7d28621728471a9b52a13-deplofc5w9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741584906 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1741584906/summary.json'
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 2461.08s
Shutdown handler de-registered
chaiml-nis-exp62-ftexp6_35561_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-exp62-ftexp6_35561_v1 status is now torndown due to DeploymentManager action