chaiml-ir-v1-3-sft-adj-_65815

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v1-3-sft-adj-_65815_v1

model_name: chaiml-ir-v1-3-sft-adj-_65815_v1

model_group: ChaiML/ir-v1-3-sft_adj-c

status: inactive

timestamp: 2025-10-26T03:22:16+00:00

num_battles: 5486

num_wins: 2999

celo_rating: 1301.38

family_friendly_score: 0.4668

family_friendly_standard_error: 0.00705546256456655

submission_type: basic

model_repo: ChaiML/ir-v1-3-sft_adj-cosinelr2e6g32

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': 0.3846803782377516, 'latency_mean': 2.599462305307388, 'latency_p50': 2.6000614166259766, 'latency_p90': 2.8508991241455077}, {'batch_size': 2, 'throughput': 0.5721751913176828, 'latency_mean': 3.492548222541809, 'latency_p50': 3.4837563037872314, 'latency_p90': 3.785895323753357}, {'batch_size': 3, 'throughput': 0.7048721629810035, 'latency_mean': 4.243716777563095, 'latency_p50': 4.223077178001404, 'latency_p90': 4.759354209899902}, {'batch_size': 4, 'throughput': 0.7960747839527021, 'latency_mean': 5.005260108709336, 'latency_p50': 5.032208442687988, 'latency_p90': 5.741421031951904}, {'batch_size': 5, 'throughput': 0.8541248089424989, 'latency_mean': 5.8279503417015075, 'latency_p50': 5.866387724876404, 'latency_p90': 6.657226276397705}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ir-v1-3-sft-adj-_65815_v1

is_internal_developer: True

language_model: ChaiML/ir-v1-3-sft_adj-cosinelr2e6g32

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-10-25

win_ratio: 0.546664236237696

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': ['</s>', 'You:', 'User:', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-ir-v1-3-sft-adj-65815-v1-mkmlizer
Waiting for job on chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer to finish
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: Downloaded to shared memory in 66.286s
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: Checking if ChaiML/ir-v1-3-sft_adj-cosinelr2e6g32 already exists in ChaiML
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_pzthk1e, device:0
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: quantized model in 42.362s
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: Processed model ChaiML/ir-v1-3-sft_adj-cosinelr2e6g32 in 108.649s
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia/config.json
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia/special_tokens_map.json
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia/tokenizer_config.json
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia/tokenizer.json
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-65815-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.43it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.41it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.83it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.79it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 39.13it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.55it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.39it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.58it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.92it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.37it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 32.66it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.52it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 31.84it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.30it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.42it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.46it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 31.00it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.64it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.92it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.35it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.62it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.15it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.75it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.54it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.55it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.56it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.11it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.10it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.35it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.51it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.66it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.90it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.87it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.79it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.63it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.67it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.50it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.76it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.84it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.25it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.38it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.38it/s]
Loading 0:  60%|█████▉    | 217/363 [00:20<00:33,  4.38it/s]
Loading 0:  61%|██████    | 220/363 [00:20<00:25,  5.54it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.38it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.61it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.46it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.95it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.15it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.79it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.40it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.82it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.49it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.35it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.98it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.56it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.20it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.21it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.94it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.69it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.01it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.18it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.19it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.80it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.90it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.19it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.21it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.29it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.06it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.28it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.91it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.41it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.52it/s]
                                                            
Job chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer completed after 188.15s with status: succeeded
Stopping job with name chaiml-ir-v1-3-sft-adj-65815-v1-mkmlizer
Pipeline stage MKMLizer completed in 189.03s
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-ir-v1-3-sft-adj-65815-v1
Waiting for inference service chaiml-ir-v1-3-sft-adj-65815-v1 to be ready
Inference service chaiml-ir-v1-3-sft-adj-65815-v1 ready after 90.25525498390198s
Pipeline stage MKMLDeployer completed in 90.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.617025375366211s
Received healthy response to inference request in 2.4085021018981934s
Received healthy response to inference request in 2.365938663482666s
Received healthy response to inference request in 2.2700612545013428s
Received healthy response to inference request in 3.0247976779937744s
5 requests
0 failed requests
5th percentile: 2.2892367362976076
10th percentile: 2.308412218093872
20th percentile: 2.346763181686401
30th percentile: 2.3744513511657717
40th percentile: 2.3914767265319825
50th percentile: 2.4085021018981934
60th percentile: 2.4919114112854004
70th percentile: 2.5753207206726074
80th percentile: 2.698579835891724
90th percentile: 2.861688756942749
95th percentile: 2.9432432174682615
99th percentile: 3.008486785888672
mean time: 2.5372650146484377
Pipeline stage StressChecker completed in 13.94s
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 0.92s
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 0.64s
Shutdown handler de-registered
chaiml-ir-v1-3-sft-adj-_65815_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 0.10s
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-ir-v1-3-sft-adj-65815-v1-profiler
Waiting for inference service chaiml-ir-v1-3-sft-adj-65815-v1-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 3238.54s
Shutdown handler de-registered
chaiml-ir-v1-3-sft-adj-_65815_v1 status is now inactive due to auto deactivation removed underperforming models