chaiml-ir-v0-2-sft

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v0-2-sft_v1

model_name: chaiml-ir-v0-2-sft_v1

model_group: ChaiML/ir-v0-2-sft

status: inactive

timestamp: 2025-10-23T00:56:08+00:00

num_battles: 5338

num_wins: 2863

celo_rating: 1295.94

family_friendly_score: 0.4778

family_friendly_standard_error: 0.007064094563353466

submission_type: basic

model_repo: ChaiML/ir-v0-2-sft

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': 0.38040100384829667, 'latency_mean': 2.6287063717842103, 'latency_p50': 2.636648178100586, 'latency_p90': 2.8844891786575317}, {'batch_size': 2, 'throughput': 0.5679079962843446, 'latency_mean': 3.520364274978638, 'latency_p50': 3.5022950172424316, 'latency_p90': 3.8508760213851927}, {'batch_size': 3, 'throughput': 0.6960205608754778, 'latency_mean': 4.290923855304718, 'latency_p50': 4.308136940002441, 'latency_p90': 4.872182989120483}, {'batch_size': 4, 'throughput': 0.7927140105628593, 'latency_mean': 5.034178018569946, 'latency_p50': 5.081110000610352, 'latency_p90': 5.479065775871277}, {'batch_size': 5, 'throughput': 0.8567555568791113, 'latency_mean': 5.800082657337189, 'latency_p50': 5.823120713233948, 'latency_p90': 6.58985447883606}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ir-v0-2-sft_v1

is_internal_developer: True

language_model: ChaiML/ir-v0-2-sft

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-10-22

win_ratio: 0.5363431997002622

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>', 'User:', 'You:'], '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-v0-2-sft-v1-mkmlizer
Waiting for job on chaiml-ir-v0-2-sft-v1-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
chaiml-ir-v0-2-sft-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v0-2-sft-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v0-2-sft-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v0-2-sft-v1-mkmlizer: Downloaded to shared memory in 64.856s
chaiml-ir-v0-2-sft-v1-mkmlizer: Checking if ChaiML/ir-v0-2-sft already exists in ChaiML
chaiml-ir-v0-2-sft-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9hi3pfc5, device:0
chaiml-ir-v0-2-sft-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v0-2-sft-v1-mkmlizer: quantized model in 42.754s
chaiml-ir-v0-2-sft-v1-mkmlizer: Processed model ChaiML/ir-v0-2-sft in 107.610s
chaiml-ir-v0-2-sft-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v0-2-sft-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v0-2-sft-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia
chaiml-ir-v0-2-sft-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia/special_tokens_map.json
chaiml-ir-v0-2-sft-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia/config.json
chaiml-ir-v0-2-sft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia/tokenizer_config.json
chaiml-ir-v0-2-sft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia/tokenizer.json
chaiml-ir-v0-2-sft-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v0-2-sft-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v0-2-sft-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v0-2-sft-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.69it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.85it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.22it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.61it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:08, 37.48it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.57it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 26.08it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.14it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.75it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.35it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.83it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.04it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.20it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.17it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.28it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.27it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.60it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.24it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:09, 29.94it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:08, 31.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.24it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.04it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 25.64it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 28.65it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.66it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 31.84it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.33it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.89it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.41it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.49it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.00it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.33it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.45it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.79it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.93it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 32.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.25it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.24it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 29.01it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.44it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 24.13it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:58,  2.61it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:40,  3.64it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.64it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  5.92it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.12it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.41it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:08, 15.56it/s]
Loading 0:  66%|██████▌   | 240/363 [00:21<00:07, 15.93it/s]
Loading 0:  67%|██████▋   | 244/363 [00:21<00:06, 19.43it/s]
Loading 0:  68%|██████▊   | 248/363 [00:21<00:05, 19.63it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.65it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 34.31it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.43it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.12it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.90it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.43it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 32.66it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 31.33it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 29.07it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.46it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:02, 25.43it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.13it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 29.80it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.31it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.78it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.67it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.28it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.93it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.51it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.94it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.68it/s]
                                                            
Job chaiml-ir-v0-2-sft-v1-mkmlizer completed after 186.05s with status: succeeded
Stopping job with name chaiml-ir-v0-2-sft-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.58s
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-v0-2-sft-v1
Waiting for inference service chaiml-ir-v0-2-sft-v1 to be ready
Inference service chaiml-ir-v0-2-sft-v1 ready after 80.41957688331604s
Pipeline stage MKMLDeployer completed in 80.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.80409574508667s
Received healthy response to inference request in 2.4009435176849365s
Received healthy response to inference request in 2.145599365234375s
Received healthy response to inference request in 2.6566171646118164s
Received healthy response to inference request in 2.373203754425049s
5 requests
0 failed requests
5th percentile: 2.19112024307251
10th percentile: 2.2366411209106447
20th percentile: 2.327682876586914
30th percentile: 2.3787517070770265
40th percentile: 2.3898476123809815
50th percentile: 2.4009435176849365
60th percentile: 2.5032129764556883
70th percentile: 2.6054824352264405
80th percentile: 2.686112880706787
90th percentile: 2.7451043128967285
95th percentile: 2.774600028991699
99th percentile: 2.7981966018676756
mean time: 2.476091909408569
Pipeline stage StressChecker completed in 14.07s
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 0.91s
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-ir-v0-2-sft_v1 status is now deployed due to DeploymentManager action
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 3137.82s
Shutdown handler de-registered
chaiml-ir-v0-2-sft_v1 status is now inactive due to auto deactivation removed underperforming models