chaiml-ir-v3-3-dpo-irv0_93712

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-3-dpo-irv0_93712_v1

model_name: training123

model_group: ChaiML/ir-v3-3-dpo_irv0f

status: torndown

timestamp: 2025-11-17T11:36:31+00:00

num_battles: 6184

num_wins: 3198

celo_rating: 1293.49

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v3-3-dpo_irv0fullpyg-cosine

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': 0.38024018090219175, 'latency_mean': 2.6297938692569733, 'latency_p50': 2.6219948530197144, 'latency_p90': 2.88732750415802}, {'batch_size': 2, 'throughput': 0.5644456672675875, 'latency_mean': 3.536092395782471, 'latency_p50': 3.536728620529175, 'latency_p90': 3.8165935277938843}, {'batch_size': 3, 'throughput': 0.6916971084717809, 'latency_mean': 4.319985262155533, 'latency_p50': 4.3459625244140625, 'latency_p90': 5.0044105529785154}, {'batch_size': 4, 'throughput': 0.7967727177652603, 'latency_mean': 4.99979082942009, 'latency_p50': 5.002950310707092, 'latency_p90': 5.661358547210693}, {'batch_size': 5, 'throughput': 0.8535388107505092, 'latency_mean': 5.841553965806961, 'latency_p50': 5.879955410957336, 'latency_p90': 6.700468420982361}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-3-dpo_irv0fullpyg-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-14

win_ratio: 0.5171410090556274

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:', '</s>', '\n', 'User:'], '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-v3-3-dpo-irv0-93712-v1-mkmlizer
Waiting for job on chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer to finish
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv0-93712-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-v3-3-dpo-irv0-93712-v1-mkmlizer: Downloaded to shared memory in 56.978s
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: Checking if ChaiML/ir-v3-3-dpo_irv0fullpyg-cosine already exists in ChaiML
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpain_p4k8, device:0
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: quantized model in 41.830s
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: Processed model ChaiML/ir-v3-3-dpo_irv0fullpyg-cosine in 98.809s
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia/config.json
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia/tokenizer.json
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv0-93712-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.37it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.14it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.43it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.81it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.15it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.93it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.09it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.31it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.34it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.19it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.47it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.47it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.19it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.12it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.28it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.67it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 28.37it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.71it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.99it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 29.48it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 31.95it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.69it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 33.47it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 34.73it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 34.88it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 36.04it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.89it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 34.47it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 28.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 26.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.91it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 32.80it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.70it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.99it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.73it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 32.61it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 31.53it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 27.91it/s]
Loading 0:  55%|█████▌    | 201/363 [00:18<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  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 [00:19<00:24,  5.72it/s]
Loading 0:  62%|██████▏   | 226/363 [00:19<00:19,  7.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.67it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.50it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:06, 19.46it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.06it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 24.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:04, 25.01it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:03, 31.97it/s]
Loading 0:  74%|███████▍  | 270/363 [00:21<00:04, 23.05it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.90it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 30.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 29.85it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 33.00it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.38it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.06it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 28.97it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.75it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 26.28it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 31.94it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.69it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.96it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.34it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.94it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.53it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 15.95it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 18.30it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 25.40it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 26.15it/s]
                                                            
Job chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer completed after 176.11s with status: succeeded
Stopping job with name chaiml-ir-v3-3-dpo-irv0-93712-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.93s
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-v3-3-dpo-irv0-93712-v1
Waiting for inference service chaiml-ir-v3-3-dpo-irv0-93712-v1 to be ready
Inference service chaiml-ir-v3-3-dpo-irv0-93712-v1 ready after 160.68232321739197s
Pipeline stage MKMLDeployer completed in 161.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.551727533340454s
Received healthy response to inference request in 2.260078191757202s
Received healthy response to inference request in 2.4535655975341797s
Received healthy response to inference request in 2.184300184249878s
Received healthy response to inference request in 2.2300658226013184s
5 requests
0 failed requests
5th percentile: 2.193453311920166
10th percentile: 2.202606439590454
20th percentile: 2.2209126949310303
30th percentile: 2.236068296432495
40th percentile: 2.2480732440948485
50th percentile: 2.260078191757202
60th percentile: 2.337473154067993
70th percentile: 2.414868116378784
80th percentile: 2.4731979846954344
90th percentile: 2.5124627590179442
95th percentile: 2.5320951461791994
99th percentile: 2.547801055908203
mean time: 2.3359474658966066
Pipeline stage StressChecker completed in 13.02s
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 0.95s
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 0.67s
Shutdown handler de-registered
chaiml-ir-v3-3-dpo-irv0_93712_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-v3-3-dpo-irv0-93712-v1-profiler
Waiting for inference service chaiml-ir-v3-3-dpo-irv0-93712-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5983.27s
Shutdown handler de-registered
chaiml-ir-v3-3-dpo-irv0_93712_v1 status is now torndown due to DeploymentManager action