chaiml-ir-v1-3-sft-adj-_24517

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v1-3-sft-adj-_24517_v1

model_name: chaiml-ir-v1-3-sft-adj-_24517_v1

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

status: inactive

timestamp: 2025-10-25T23:49:36+00:00

num_battles: 6149

num_wins: 3309

celo_rating: 1292.28

family_friendly_score: 0.4648

family_friendly_standard_error: 0.007053523374881521

submission_type: basic

model_repo: ChaiML/ir-v1-3-sft_adj-cosinelr5e6g32

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': 0.3831199297469262, 'latency_mean': 2.6100469982624053, 'latency_p50': 2.602534294128418, 'latency_p90': 2.8706644058227537}, {'batch_size': 2, 'throughput': 0.5734432586585178, 'latency_mean': 3.482514853477478, 'latency_p50': 3.50665819644928, 'latency_p90': 3.777558135986328}, {'batch_size': 3, 'throughput': 0.7113241095218055, 'latency_mean': 4.2129806756973265, 'latency_p50': 4.210851192474365, 'latency_p90': 4.85612804889679}, {'batch_size': 4, 'throughput': 0.8067641094239068, 'latency_mean': 4.92342205286026, 'latency_p50': 4.938722014427185, 'latency_p90': 5.635236120223999}, {'batch_size': 5, 'throughput': 0.8791011431927843, 'latency_mean': 5.655422621965409, 'latency_p50': 5.660549283027649, 'latency_p90': 6.397869873046875}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ir-v1-3-sft-adj-_24517_v1

is_internal_developer: True

language_model: ChaiML/ir-v1-3-sft_adj-cosinelr5e6g32

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-10-25

win_ratio: 0.5381362823223288

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': ['User:', '\n', 'You:', '</s>'], '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-24517-v1-mkmlizer
Waiting for job on chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer to finish
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: Downloaded to shared memory in 83.787s
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: Checking if ChaiML/ir-v1-3-sft_adj-cosinelr5e6g32 already exists in ChaiML
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe0r2o8c2, device:0
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: quantized model in 41.671s
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: Processed model ChaiML/ir-v1-3-sft_adj-cosinelr5e6g32 in 125.458s
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia/special_tokens_map.json
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia/config.json
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia/tokenizer_config.json
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia/tokenizer.json
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v1-3-sft-adj-24517-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.47it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.21it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.64it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.13it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.59it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.00it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.46it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.69it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.71it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.23it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.63it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.60it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.90it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.51it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.50it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.86it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.30it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.43it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.81it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.04it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.48it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.02it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.13it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.09it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.89it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.35it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.10it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.57it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.83it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.94it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.12it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.73it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.10it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.07it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.07it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.44it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.16it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.75it/s]
Loading 0:  60%|██████    | 219/363 [00:19<00:28,  4.99it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.01it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13,  9.65it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:10, 12.04it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 15.00it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 17.30it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 21.87it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.41it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:03, 27.82it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.50it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.52it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.39it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.63it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 30.46it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.89it/s]
Loading 0:  83%|████████▎ | 303/363 [00:22<00:01, 33.92it/s]
Loading 0:  85%|████████▍ | 307/363 [00:22<00:02, 20.22it/s]
Loading 0:  86%|████████▌ | 311/363 [00:22<00:02, 20.04it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 27.68it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 27.93it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 31.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 30.80it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.20it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.26it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.38it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.98it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.48it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.08it/s]
                                                            
Job chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer completed after 196.56s with status: succeeded
Stopping job with name chaiml-ir-v1-3-sft-adj-24517-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.48s
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-24517-v1
Waiting for inference service chaiml-ir-v1-3-sft-adj-24517-v1 to be ready
Inference service chaiml-ir-v1-3-sft-adj-24517-v1 ready after 80.24207282066345s
Pipeline stage MKMLDeployer completed in 80.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9594926834106445s
Received healthy response to inference request in 2.4239165782928467s
Received healthy response to inference request in 2.175201654434204s
Received healthy response to inference request in 2.5972399711608887s
Received healthy response to inference request in 2.4005191326141357s
5 requests
0 failed requests
5th percentile: 2.2202651500701904
10th percentile: 2.2653286457061768
20th percentile: 2.3554556369781494
30th percentile: 2.4051986217498778
40th percentile: 2.414557600021362
50th percentile: 2.4239165782928467
60th percentile: 2.4932459354400636
70th percentile: 2.5625752925872805
80th percentile: 2.6696905136108398
90th percentile: 2.8145915985107424
95th percentile: 2.8870421409606934
99th percentile: 2.9450025749206543
mean time: 2.511274003982544
Pipeline stage StressChecker completed in 13.91s
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 0.61s
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-_24517_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v1-3-sft-adj-24517-v1-profiler
Waiting for inference service chaiml-ir-v1-3-sft-adj-24517-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 3110.17s
Shutdown handler de-registered
chaiml-ir-v1-3-sft-adj-_24517_v1 status is now inactive due to auto deactivation removed underperforming models