chaiml-exp111-sft-superm_7898

developer_uid: NischayDnk

submission_id: chaiml-exp111-sft-superm_7898_v2

model_name: chaiml-exp111-sft-superm_7898_v2

model_group: ChaiML/exp111-SFT-superm

status: torndown

timestamp: 2025-03-21T04:24:21+00:00

num_battles: 9939

num_wins: 4933

celo_rating: 1281.12

family_friendly_score: 0.5724

family_friendly_standard_error: 0.006996545433283485

submission_type: basic

model_repo: ChaiML/exp111-SFT-supermega4M-2e

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.36840869219212063, 'latency_mean': 2.7143110072612764, 'latency_p50': 2.713167667388916, 'latency_p90': 2.9909847736358643}, {'batch_size': 2, 'throughput': 0.5737306627111795, 'latency_mean': 3.4824375748634337, 'latency_p50': 3.479691505432129, 'latency_p90': 3.8224851846694947}, {'batch_size': 3, 'throughput': 0.7285021237445852, 'latency_mean': 4.109695143699646, 'latency_p50': 4.09538733959198, 'latency_p90': 4.578469586372376}, {'batch_size': 4, 'throughput': 0.8493665485889054, 'latency_mean': 4.677167649269104, 'latency_p50': 4.625481128692627, 'latency_p90': 5.1885683059692385}, {'batch_size': 5, 'throughput': 0.9345206327590101, 'latency_mean': 5.325097739696503, 'latency_p50': 5.34313440322876, 'latency_p90': 5.9526979446411135}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp111-sft-superm_7898_v2

is_internal_developer: False

language_model: ChaiML/exp111-SFT-supermega4M-2e

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-03-20

win_ratio: 0.4963275983499346

generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, '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-exp111-sft-superm-7898-v2-mkmlizer
Waiting for job on chaiml-exp111-sft-superm-7898-v2-mkmlizer to finish
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║                                                                     ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║                                                                     ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║                                                                     ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ║                                                                     ║
chaiml-exp111-sft-superm-7898-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp111-sft-superm-7898-v2-mkmlizer: Downloaded to shared memory in 69.128s
chaiml-exp111-sft-superm-7898-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph2dhj_e_, device:0
chaiml-exp111-sft-superm-7898-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp111-sft-superm-7898-v2-mkmlizer: quantized model in 53.126s
chaiml-exp111-sft-superm-7898-v2-mkmlizer: Processed model ChaiML/exp111-SFT-supermega4M-2e in 122.254s
chaiml-exp111-sft-superm-7898-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp111-sft-superm-7898-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp111-sft-superm-7898-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp111-sft-superm-7898-v2
chaiml-exp111-sft-superm-7898-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp111-sft-superm-7898-v2/special_tokens_map.json
chaiml-exp111-sft-superm-7898-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp111-sft-superm-7898-v2/tokenizer_config.json
chaiml-exp111-sft-superm-7898-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp111-sft-superm-7898-v2/tokenizer.json
chaiml-exp111-sft-superm-7898-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp111-sft-superm-7898-v2/flywheel_model.0.safetensors
chaiml-exp111-sft-superm-7898-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.64it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 38.91it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.90it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.03it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.09it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.38it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.89it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.53it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.45it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.73it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 31.42it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 29.71it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 30.24it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 27.32it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.12it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.59it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.55it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 25.07it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.52it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 28.48it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.75it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.75it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 23.79it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:09, 26.97it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 24.38it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.96it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.59it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.11it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.90it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 29.27it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:05, 35.89it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 23.75it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 23.01it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:09, 21.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 25.51it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.80it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.88it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.91it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.01it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.93it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.82it/s]
Loading 0:  53%|█████▎    | 193/363 [00:06<00:06, 24.35it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.47it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.47it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:29,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.16it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.34it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.41it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.43it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.03it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 14.96it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.56it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.01it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.18it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.83it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.55it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:03, 31.73it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.50it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.96it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 24.93it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.13it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.79it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 29.91it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.83it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 29.09it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.72it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.53it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.28it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 23.33it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.21it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 23.68it/s]
Loading 0:  90%|████████▉ | 325/363 [00:26<00:01, 26.84it/s]
Loading 0:  90%|█████████ | 328/363 [00:26<00:01, 26.41it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 25.37it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:01, 26.45it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 25.79it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:14,  1.53it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:06,  2.66it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.37it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.68it/s]
                                                            
Job chaiml-exp111-sft-superm-7898-v2-mkmlizer completed after 154.69s with status: succeeded
Stopping job with name chaiml-exp111-sft-superm-7898-v2-mkmlizer
Pipeline stage MKMLizer completed in 155.17s
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-exp111-sft-superm-7898-v2
Waiting for inference service chaiml-exp111-sft-superm-7898-v2 to be ready
Inference service chaiml-exp111-sft-superm-7898-v2 ready after 90.51287245750427s
Pipeline stage MKMLDeployer completed in 91.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4296066761016846s
Received healthy response to inference request in 2.3797311782836914s
Received healthy response to inference request in 2.580225944519043s
Received healthy response to inference request in 2.4086191654205322s
Received healthy response to inference request in 2.347001075744629s
5 requests
0 failed requests
5th percentile: 2.3535470962524414
10th percentile: 2.360093116760254
20th percentile: 2.373185157775879
30th percentile: 2.3855087757110596
40th percentile: 2.397063970565796
50th percentile: 2.4086191654205322
60th percentile: 2.4772618770599366
70th percentile: 2.545904588699341
80th percentile: 2.7501020908355716
90th percentile: 3.089854383468628
95th percentile: 3.259730529785156
99th percentile: 3.395631446838379
mean time: 2.629036808013916
Pipeline stage StressChecker completed in 14.79s
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 0.83s
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 0.80s
Shutdown handler de-registered
chaiml-exp111-sft-superm_7898_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp111-sft-superm-7898-v2-profiler
Waiting for inference service chaiml-exp111-sft-superm-7898-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 2810.63s
Shutdown handler de-registered
chaiml-exp111-sft-superm_7898_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp111-sft-superm_7898_v2 status is now torndown due to DeploymentManager action