chaiml-ss-new-v4-full-lr2e6

developer_uid: chai_backend_admin

submission_id: chaiml-ss-new-v4-full-lr2e6_v2

model_name: chaiml-ss-new-v4-full-lr2e6_v2

model_group: ChaiML/ss-new-v4-full-lr

status: inactive

timestamp: 2025-10-04T19:56:13+00:00

num_battles: 7321

num_wins: 3693

celo_rating: 1293.87

family_friendly_score: 0.498

family_friendly_standard_error: 0.0070710112430967045

submission_type: basic

model_repo: ChaiML/ss-new-v4-full-lr2e6

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.37650152432366935, 'latency_mean': 2.655924478769302, 'latency_p50': 2.67106831073761, 'latency_p90': 2.912551832199097}, {'batch_size': 2, 'throughput': 0.5700770299219213, 'latency_mean': 3.499709093570709, 'latency_p50': 3.4879064559936523, 'latency_p90': 3.805601143836975}, {'batch_size': 3, 'throughput': 0.7002445012625905, 'latency_mean': 4.259669090509415, 'latency_p50': 4.266454577445984, 'latency_p90': 5.025662088394165}, {'batch_size': 4, 'throughput': 0.7976336529538328, 'latency_mean': 5.001427830457687, 'latency_p50': 5.008683681488037, 'latency_p90': 5.493585228919982}, {'batch_size': 5, 'throughput': 0.8560147535715412, 'latency_mean': 5.791999056339264, 'latency_p50': 5.816680908203125, 'latency_p90': 6.535533905029297}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ss-new-v4-full-lr2e6_v2

is_internal_developer: True

language_model: ChaiML/ss-new-v4-full-lr2e6

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-04

win_ratio: 0.5044392842507854

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '####', '####\n', '</s>', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}

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-ss-new-v4-full-lr2e6-v2-mkmlizer
Waiting for job on chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer to finish
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║                                                                     ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║                                                                     ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║                                                                     ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║                                                                     ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ║                                                                     ║
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: Downloaded to shared memory in 63.526s
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: Checking if ChaiML/ss-new-v4-full-lr2e6 already exists in ChaiML
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprm8q_qn2, device:0
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: quantized model in 41.635s
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: Processed model ChaiML/ss-new-v4-full-lr2e6 in 105.162s
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ss-new-v4-full-lr2e6-v2/nvidia
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ss-new-v4-full-lr2e6-v2/nvidia/config.json
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ss-new-v4-full-lr2e6-v2/nvidia/special_tokens_map.json
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ss-new-v4-full-lr2e6-v2/nvidia/tokenizer_config.json
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ss-new-v4-full-lr2e6-v2/nvidia/tokenizer.json
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ss-new-v4-full-lr2e6-v2/nvidia/flywheel_model.1.safetensors
Retrying (%r) after connection broken by '%r': %s
chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.80it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.77it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.98it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.21it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.79it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.40it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.95it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.56it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.77it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.70it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.77it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 31.16it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.64it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.59it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.68it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.86it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 30.41it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:08, 32.00it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:07, 32.89it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:07, 33.94it/s]
Loading 0:  30%|██▉       | 108/363 [00:03<00:09, 26.57it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:09, 26.39it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.13it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 32.66it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 33.78it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.82it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 34.39it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.91it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.60it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 25.65it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 33.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 32.08it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.06it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.04it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.65it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 29.09it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.45it/s]
Loading 0:  55%|█████▌    | 201/363 [00:18<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.46it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.88it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:21,  6.71it/s]
Loading 0:  62%|██████▏   | 226/363 [00:19<00:16,  8.35it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:12, 10.30it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.04it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.43it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.76it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:03, 28.23it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:03, 27.47it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.57it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.27it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 25.06it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 32.34it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 31.87it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 35.29it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 33.68it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 34.44it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 32.58it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 31.64it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 27.62it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 33.37it/s]
Loading 0:  89%|████████▊ | 322/363 [00:22<00:01, 32.00it/s]
Loading 0:  90%|█████████ | 327/363 [00:22<00:01, 35.49it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 33.81it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.64it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 35.08it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 20.94it/s]
Loading 0:  96%|█████████▌| 348/363 [00:23<00:00, 22.56it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 30.26it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 27.47it/s]
Loading 0: 100%|██████████| 363/363 [00:24<00:00, 29.49it/s]
                                                            
Job chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer completed after 194.8s with status: succeeded
Stopping job with name chaiml-ss-new-v4-full-lr2e6-v2-mkmlizer
Pipeline stage MKMLizer completed in 195.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ss-new-v4-full-lr2e6-v2
Waiting for inference service chaiml-ss-new-v4-full-lr2e6-v2 to be ready
Inference service chaiml-ss-new-v4-full-lr2e6-v2 ready after 60.351274251937866s
Pipeline stage MKMLDeployer completed in 60.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4531750679016113s
Received healthy response to inference request in 2.312870502471924s
Received healthy response to inference request in 2.7479054927825928s
Received healthy response to inference request in 2.080430030822754s
Received healthy response to inference request in 2.2881920337677s
5 requests
0 failed requests
5th percentile: 2.1219824314117433
10th percentile: 2.1635348320007326
20th percentile: 2.246639633178711
30th percentile: 2.293127727508545
40th percentile: 2.3029991149902345
50th percentile: 2.312870502471924
60th percentile: 2.368992328643799
70th percentile: 2.425114154815674
80th percentile: 2.512121152877808
90th percentile: 2.6300133228302003
95th percentile: 2.6889594078063963
99th percentile: 2.7361162757873534
mean time: 2.3765146255493166
Pipeline stage StressChecker completed in 13.29s
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 0.62s
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 0.60s
Shutdown handler de-registered
chaiml-ss-new-v4-full-lr2e6_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 0.08s
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-ss-new-v4-full-lr2e6-v2-profiler
Waiting for inference service chaiml-ss-new-v4-full-lr2e6-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 3127.73s
Shutdown handler de-registered
chaiml-ss-new-v4-full-lr2e6_v2 status is now inactive due to auto deactivation removed underperforming models