chaiml-ir-v4-2-dpo-ir31_75994

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-2-dpo-ir31_75994_v1

model_name: training123

model_group: ChaiML/ir-v4-2-dpo_ir31c

status: torndown

timestamp: 2025-11-07T10:21:19+00:00

num_battles: 7088

num_wins: 3705

celo_rating: 1308.87

family_friendly_score: 0.4576

family_friendly_standard_error: 0.0070455977744972075

submission_type: basic

model_repo: ChaiML/ir-v4-2-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': 0.29964897377498906, 'latency_mean': 3.3371454763412474, 'latency_p50': 2.7668715715408325, 'latency_p90': 4.962805604934692}, {'batch_size': 2, 'throughput': 0.574868951697094, 'latency_mean': 3.4749472761154174, 'latency_p50': 3.482900023460388, 'latency_p90': 3.77369430065155}, {'batch_size': 3, 'throughput': 0.7132333807953138, 'latency_mean': 4.194038736820221, 'latency_p50': 4.207093000411987, 'latency_p90': 4.8240440607070925}, {'batch_size': 4, 'throughput': 0.8071251725328717, 'latency_mean': 4.941742540597915, 'latency_p50': 4.941150784492493, 'latency_p90': 5.582431411743164}, {'batch_size': 5, 'throughput': 0.8725657442856896, 'latency_mean': 5.7100081837177274, 'latency_p50': 5.705977559089661, 'latency_p90': 6.4559382677078245}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-2-dpo_ir31cos-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-04

win_ratio: 0.522714446952596

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-v4-2-dpo-ir31-75994-v1-mkmlizer
Waiting for job on chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer to finish
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: Downloaded to shared memory in 59.171s
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: Checking if ChaiML/ir-v4-2-dpo_ir31cos-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcdnty354, device:0
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: quantized model in 42.187s
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: Processed model ChaiML/ir-v4-2-dpo_ir31cos-lr5e6b01 in 101.359s
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia/config.json
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia/tokenizer.json
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-75994-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.38it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.27it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.24it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.29it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.49it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.51it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.18it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.42it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.39it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.93it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.77it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.96it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.43it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.13it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.06it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.29it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.03it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.97it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 28.31it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.80it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.49it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.38it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.30it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.63it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.75it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.14it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.92it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.46it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 25.05it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:07, 27.76it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:06, 29.33it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.65it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.73it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.44it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.23it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.23it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.38it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.25it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.94it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:16,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.42it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:30,  4.83it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:21,  6.64it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:16,  8.21it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:13, 10.11it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 15.86it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.94it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.17it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.35it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.63it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.70it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.57it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.64it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.44it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.55it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.82it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.12it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.71it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.47it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.78it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.90it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 26.76it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.39it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.77it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.25it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.65it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.66it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.27it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.61it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 20.59it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 26.92it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 26.25it/s]
                                                            
Job chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer completed after 174.4s with status: succeeded
Stopping job with name chaiml-ir-v4-2-dpo-ir31-75994-v1-mkmlizer
Pipeline stage MKMLizer completed in 174.92s
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-v4-2-dpo-ir31-75994-v1
Waiting for inference service chaiml-ir-v4-2-dpo-ir31-75994-v1 to be ready
Inference service chaiml-ir-v4-2-dpo-ir31-75994-v1 ready after 140.52168250083923s
Pipeline stage MKMLDeployer completed in 140.96s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.500389337539673s
Received healthy response to inference request in 2.1288950443267822s
Received healthy response to inference request in 2.5220725536346436s
Received healthy response to inference request in 2.1933767795562744s
5 requests
1 failed requests
5th percentile: 2.1417913913726805
10th percentile: 2.154687738418579
20th percentile: 2.180480432510376
30th percentile: 2.2547792911529543
40th percentile: 2.3775843143463136
50th percentile: 2.500389337539673
60th percentile: 2.509062623977661
70th percentile: 2.5177359104156496
80th percentile: 6.099017715454105
90th percentile: 13.252908039093018
95th percentile: 16.829853200912474
99th percentile: 19.691409330368042
mean time: 5.950306415557861
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1163790225982666s
Received healthy response to inference request in 2.2756471633911133s
Received healthy response to inference request in 2.4922313690185547s
Received healthy response to inference request in 2.138939619064331s
Received healthy response to inference request in 2.1261563301086426s
5 requests
0 failed requests
5th percentile: 2.118334484100342
10th percentile: 2.120289945602417
20th percentile: 2.124200868606567
30th percentile: 2.1287129878997804
40th percentile: 2.1338263034820555
50th percentile: 2.138939619064331
60th percentile: 2.1936226367950438
70th percentile: 2.248305654525757
80th percentile: 2.3189640045166016
90th percentile: 2.405597686767578
95th percentile: 2.4489145278930664
99th percentile: 2.483568000793457
mean time: 2.2298707008361816
Pipeline stage StressChecker completed in 43.43s
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 0.68s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-ir31_75994_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 3070.85s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-ir31_75994_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v4-2-dpo-ir31_75994_v1 status is now torndown due to DeploymentManager action