chaiml-ir-v4-3-dpo-irv1_15230

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-3-dpo-irv1_15230_v1

model_name: training123

model_group: ChaiML/ir-v4-3-dpo_irv13

status: inactive

timestamp: 2025-11-01T23:09:18+00:00

num_battles: 5947

num_wins: 3102

celo_rating: 1307.45

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-3-dpo_irv13-lr5e6b01-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': 0.37934445620570717, 'latency_mean': 2.63600316286087, 'latency_p50': 2.6329749822616577, 'latency_p90': 2.904091215133667}, {'batch_size': 2, 'throughput': 0.5561483547837504, 'latency_mean': 3.5900279104709627, 'latency_p50': 3.621482491493225, 'latency_p90': 3.8687996387481687}, {'batch_size': 3, 'throughput': 0.685537924660433, 'latency_mean': 4.361583685874939, 'latency_p50': 4.365604519844055, 'latency_p90': 4.677898383140564}, {'batch_size': 4, 'throughput': 0.7854130463478532, 'latency_mean': 5.080056701898575, 'latency_p50': 5.096314907073975, 'latency_p90': 5.737985134124756}, {'batch_size': 5, 'throughput': 0.8358077589108273, 'latency_mean': 5.94337568283081, 'latency_p50': 5.9640079736709595, 'latency_p90': 6.749711561203003}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-3-dpo_irv13-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.58

us_pacific_date: 2025-11-01

win_ratio: 0.5216075332100218

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:', '\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': '{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-v4-3-dpo-irv1-15230-v1-mkmlizer
Waiting for job on chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer to finish
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: Downloaded to shared memory in 58.679s
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: Checking if ChaiML/ir-v4-3-dpo_irv13-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfrwyvqr8, device:0
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: quantized model in 42.688s
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: Processed model ChaiML/ir-v4-3-dpo_irv13-lr5e6b01-cosine in 101.368s
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia/config.json
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia/tokenizer.json
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv1-15230-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.84it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.66it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.35it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.90it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.31it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.47it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.42it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.37it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.24it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.64it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.98it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.20it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.94it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.79it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.75it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.05it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.82it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 26.97it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.21it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.42it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.91it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.20it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.92it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 31.95it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.77it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.27it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.18it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.78it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.25it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.61it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.62it/s]
Loading 0:  45%|████▍     | 163/363 [00:05<00:06, 28.68it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:07, 26.36it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 32.95it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.44it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.41it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.74it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.85it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.09it/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 [00:19<01:14,  2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.38it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.77it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:21,  6.54it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.09it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:13,  9.96it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 15.58it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 16.61it/s]
Loading 0:  67%|██████▋   | 245/363 [00:21<00:06, 19.33it/s]
Loading 0:  69%|██████▊   | 249/363 [00:21<00:06, 18.12it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 23.07it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 24.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:03, 30.96it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 22.54it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.49it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.84it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.10it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.82it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.82it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.07it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.11it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.56it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.78it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.45it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.54it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.53it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.23it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.08it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 19.21it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 26.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 26.28it/s]
                                                            
Job chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer completed after 165.12s with status: succeeded
Stopping job with name chaiml-ir-v4-3-dpo-irv1-15230-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-3-dpo-irv1-15230-v1
Waiting for inference service chaiml-ir-v4-3-dpo-irv1-15230-v1 to be ready
Failed to get response for submission chaiml-nitral-dpos1-bet_5231_v12: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-nitral-dpos1-bet_5231_v12/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n  Field required [type=missing, input_value={\'detail\': \\"503, message=...-bet_5231_v12/predict\'\\"}, input_type=dict]\\n    For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
Inference service chaiml-ir-v4-3-dpo-irv1-15230-v1 ready after 130.6640248298645s
Pipeline stage MKMLDeployer completed in 131.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.81467342376709s
Received healthy response to inference request in 2.5363194942474365s
Received healthy response to inference request in 2.753168821334839s
Received healthy response to inference request in 2.493027687072754s
Received healthy response to inference request in 2.40061092376709s
5 requests
0 failed requests
5th percentile: 2.419094276428223
10th percentile: 2.4375776290893554
20th percentile: 2.474544334411621
30th percentile: 2.5016860485076906
40th percentile: 2.5190027713775636
50th percentile: 2.5363194942474365
60th percentile: 2.6230592250823976
70th percentile: 2.7097989559173583
80th percentile: 2.7654697418212892
90th percentile: 2.7900715827941895
95th percentile: 2.8023725032806395
99th percentile: 2.8122132396698
mean time: 2.5995600700378416
Pipeline stage StressChecker completed in 14.49s
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 0.77s
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 0.95s
Shutdown handler de-registered
chaiml-ir-v4-3-dpo-irv1_15230_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-3-dpo-irv1-15230-v1-profiler
Waiting for inference service chaiml-ir-v4-3-dpo-irv1-15230-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 5828.34s
Shutdown handler de-registered