chaiml-ir-v4-1-dpo-ir31_20834

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-1-dpo-ir31_20834_v1

model_name: training123

model_group: ChaiML/ir-v4-1-dpo_ir31c

status: torndown

timestamp: 2025-11-07T11:21:19+00:00

num_battles: 5435

num_wins: 2820

celo_rating: 1304.22

family_friendly_score: 0.44499999999999995

family_friendly_standard_error: 0.007028157653325657

submission_type: basic

model_repo: ChaiML/ir-v4-1-dpo_ir31cos-lr5e6b01

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': 0.3812340699774942, 'latency_mean': 2.622944405078888, 'latency_p50': 2.6135834455490112, 'latency_p90': 2.888543725013733}, {'batch_size': 2, 'throughput': 0.5752228395459111, 'latency_mean': 3.470792167186737, 'latency_p50': 3.4400522708892822, 'latency_p90': 3.7753480195999147}, {'batch_size': 3, 'throughput': 0.7085704530073869, 'latency_mean': 4.221621873378754, 'latency_p50': 4.191150665283203, 'latency_p90': 4.839529705047608}, {'batch_size': 4, 'throughput': 0.8006180162766959, 'latency_mean': 4.962948724031448, 'latency_p50': 4.995320558547974, 'latency_p90': 5.61524851322174}, {'batch_size': 5, 'throughput': 0.8687677393504234, 'latency_mean': 5.72697356581688, 'latency_p50': 5.690793037414551, 'latency_p90': 6.495306015014648}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-1-dpo_ir31cos-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-04

win_ratio: 0.5188592456301748

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', '</s>', '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': '{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-v4-1-dpo-ir31-20834-v1-mkmlizer
Waiting for job on chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer to finish
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-v4-1-dpo-ir31-20834-v1-mkmlizer: Downloaded to shared memory in 58.257s
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: Checking if ChaiML/ir-v4-1-dpo_ir31cos-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4c7upgqh, device:0
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: quantized model in 41.959s
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: Processed model ChaiML/ir-v4-1-dpo_ir31cos-lr5e6b01 in 100.217s
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia/config.json
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia/tokenizer.json
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-20834-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.76it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.94it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.16it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.29it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 39.51it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.06it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.53it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.85it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.54it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.43it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.85it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.11it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.99it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.09it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 26.15it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.04it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.29it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.46it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:09, 30.10it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:08, 31.50it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.01it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.06it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 26.22it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.09it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.12it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.32it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.71it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.35it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.82it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.57it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.26it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.47it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.89it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.18it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.35it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.80it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.57it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.37it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.48it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.97it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.81it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:33,  4.39it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.73it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.65it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.39it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.49it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:06, 19.44it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.29it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 25.55it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.33it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.24it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.79it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.78it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 30.88it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.94it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.23it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.88it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.85it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 29.58it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.97it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:02, 23.35it/s]
Loading 0:  87%|████████▋ | 316/363 [00:23<00:01, 25.40it/s]
Loading 0:  88%|████████▊ | 320/363 [00:23<00:01, 22.75it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 30.03it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 29.61it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.07it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 32.35it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.19it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.97it/s]
                                                            
Job chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer completed after 174.94s with status: succeeded
Stopping job with name chaiml-ir-v4-1-dpo-ir31-20834-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-1-dpo-ir31-20834-v1
Waiting for inference service chaiml-ir-v4-1-dpo-ir31-20834-v1 to be ready
Inference service chaiml-ir-v4-1-dpo-ir31-20834-v1 ready after 140.7422218322754s
Pipeline stage MKMLDeployer completed in 141.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8062021732330322s
Received healthy response to inference request in 2.094724655151367s
Received healthy response to inference request in 2.345331907272339s
Received healthy response to inference request in 2.3058125972747803s
Received healthy response to inference request in 2.2102456092834473s
5 requests
0 failed requests
5th percentile: 2.117828845977783
10th percentile: 2.140933036804199
20th percentile: 2.1871414184570312
30th percentile: 2.229359006881714
40th percentile: 2.267585802078247
50th percentile: 2.3058125972747803
60th percentile: 2.321620321273804
70th percentile: 2.3374280452728273
80th percentile: 2.4375059604644775
90th percentile: 2.621854066848755
95th percentile: 2.7140281200408936
99th percentile: 2.7877673625946047
mean time: 2.352463388442993
Pipeline stage StressChecker completed in 13.42s
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 0.69s
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-v4-1-dpo-ir31_20834_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-1-dpo-ir31-20834-v1-profiler
Waiting for inference service chaiml-ir-v4-1-dpo-ir31-20834-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 3190.74s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-ir31_20834_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v4-1-dpo-ir31_20834_v1 status is now torndown due to DeploymentManager action