chaiml-ir-v4-3-dpo-irv0_37406

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-3-dpo-irv0_37406_v1

model_name: training123

model_group: ChaiML/ir-v4-3-dpo_irv0-

status: inactive

timestamp: 2025-11-01T23:22:34+00:00

num_battles: 5745

num_wins: 2903

celo_rating: 1300.14

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-3-dpo_irv0-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': 0.37932626595173025, 'latency_mean': 2.6361351346969606, 'latency_p50': 2.621811628341675, 'latency_p90': 2.891697883605957}, {'batch_size': 2, 'throughput': 0.5694737116967212, 'latency_mean': 3.5065361404418947, 'latency_p50': 3.4923735857009888, 'latency_p90': 3.813736152648926}, {'batch_size': 3, 'throughput': 0.7102260396650595, 'latency_mean': 4.210790510177612, 'latency_p50': 4.191932678222656, 'latency_p90': 4.666678237915039}, {'batch_size': 4, 'throughput': 0.7973407522192131, 'latency_mean': 4.998045438528061, 'latency_p50': 5.045767307281494, 'latency_p90': 5.532509350776673}, {'batch_size': 5, 'throughput': 0.8568893955596981, 'latency_mean': 5.801693102121353, 'latency_p50': 5.799582839012146, 'latency_p90': 6.60262360572815}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-3-dpo_irv0-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-01

win_ratio: 0.5053089643167972

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:', '</s>', '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-irv0-37406-v1-mkmlizer
Waiting for job on chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer to finish
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: Downloaded to shared memory in 61.102s
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: Checking if ChaiML/ir-v4-3-dpo_irv0-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4ujuomoi, device:0
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: quantized model in 42.054s
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: Processed model ChaiML/ir-v4-3-dpo_irv0-lr5e6b01 in 103.157s
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv0-37406-v1/nvidia
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv0-37406-v1/nvidia/config.json
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv0-37406-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv0-37406-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv0-37406-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-3-dpo-irv0-37406-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.36it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.21it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.29it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.70it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.96it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.25it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.64it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.34it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.78it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.01it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.12it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.33it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.08it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.08it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.30it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.44it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.30it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.86it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.79it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.33it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.80it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.34it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.20it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.33it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.54it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.21it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.49it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.70it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.25it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.05it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.98it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.04it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.52it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.38it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.00it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.75it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 29.80it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.89it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.93it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:44,  3.36it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.68it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.86it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.81it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13, 10.01it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 11.91it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.42it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.62it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 23.38it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.60it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.07it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.97it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.17it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.92it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.38it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.50it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.57it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.76it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.18it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.04it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.14it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.31it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.52it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.80it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.65it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.84it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.20it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.13it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.65it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.70it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.05it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.55it/s]
                                                            
Job chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer completed after 154.9s with status: succeeded
Stopping job with name chaiml-ir-v4-3-dpo-irv0-37406-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-3-dpo-irv0-37406-v1
Waiting for inference service chaiml-ir-v4-3-dpo-irv0-37406-v1 to be ready
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', '')
Failed to get response for submission chaiml-prm-v0-2-pair-ll_56078_v1: HTTPConnectionPool(host='chaiml-prm-v0-2-pair-ll-56078-v1-predictor.creator-studio.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-ir-v4-3-dpo-irv0-37406-v1 ready after 130.6240038871765s
Pipeline stage MKMLDeployer completed in 140.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.362137794494629s
Received healthy response to inference request in 2.248508930206299s
Received healthy response to inference request in 2.880686044692993s
Received healthy response to inference request in 2.2749624252319336s
Received healthy response to inference request in 2.1593210697174072s
5 requests
0 failed requests
5th percentile: 2.1771586418151854
10th percentile: 2.194996213912964
20th percentile: 2.2306713581085207
30th percentile: 2.253799629211426
40th percentile: 2.2643810272216798
50th percentile: 2.2749624252319336
60th percentile: 2.5172518730163573
70th percentile: 2.759541320800781
80th percentile: 2.9769763946533203
90th percentile: 3.1695570945739746
95th percentile: 3.2658474445343018
99th percentile: 3.3428797245025637
mean time: 2.5851232528686525
Pipeline stage StressChecker completed in 16.93s
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 0.72s
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 0.66s
Shutdown handler de-registered
chaiml-ir-v4-3-dpo-irv0_37406_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-v4-3-dpo-irv0-37406-v1-profiler
Waiting for inference service chaiml-ir-v4-3-dpo-irv0-37406-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 5211.43s
Shutdown handler de-registered