chaiml-ir-v4-dpo-irv0-l_29534

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-dpo-irv0-l_29534_v1

model_name: training123

model_group: ChaiML/ir-v4-dpo_irv0-lr

status: inactive

timestamp: 2025-10-29T17:46:53+00:00

num_battles: 6075

num_wins: 3129

celo_rating: 1302.65

family_friendly_score: 0.48540000000000005

family_friendly_standard_error: 0.007068052631382989

submission_type: basic

model_repo: ChaiML/ir-v4-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': 0.3831771874460771, 'latency_mean': 2.609663163423538, 'latency_p50': 2.6088879108428955, 'latency_p90': 2.873037648200989}, {'batch_size': 2, 'throughput': 0.5734116366189735, 'latency_mean': 3.487792776823044, 'latency_p50': 3.496007800102234, 'latency_p90': 3.8217348575592043}, {'batch_size': 3, 'throughput': 0.7129274495434739, 'latency_mean': 4.206626538038254, 'latency_p50': 4.199029088020325, 'latency_p90': 4.53911144733429}, {'batch_size': 4, 'throughput': 0.8071205572839327, 'latency_mean': 4.936457117795944, 'latency_p50': 4.938569188117981, 'latency_p90': 5.547393584251403}, {'batch_size': 5, 'throughput': 0.8684459034272015, 'latency_mean': 5.73252646446228, 'latency_p50': 5.736232161521912, 'latency_p90': 6.493347024917602}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-dpo_irv0-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-10-29

win_ratio: 0.5150617283950617

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:', 'You:', '\n', '</s>'], '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-dpo-irv0-l-29534-v1-mkmlizer
Waiting for job on chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer to finish
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: Downloaded to shared memory in 69.753s
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: Checking if ChaiML/ir-v4-dpo_irv0-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpijmv78mv, device:0
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: quantized model in 41.810s
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: Processed model ChaiML/ir-v4-dpo_irv0-lr5e6b01 in 111.564s
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia/config.json
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia/tokenizer.json
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-29534-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.66it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.19it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.02it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.17it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.33it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:11, 29.08it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:12, 26.39it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.30it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.62it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.91it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.11it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.31it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.42it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.31it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.30it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.75it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.05it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 27.33it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.82it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.54it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.98it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.64it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.27it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.17it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.30it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.82it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 32.86it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.15it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.96it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.60it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.25it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.13it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.23it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.49it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.57it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.45it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.33it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.83it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.97it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.14it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:53,  2.84it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:32,  4.43it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:24,  5.78it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.53it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.53it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 19.52it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.07it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 25.41it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.28it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 33.49it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 23.62it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:04, 21.32it/s]
Loading 0:  77%|███████▋  | 280/363 [00:21<00:03, 25.47it/s]
Loading 0:  78%|███████▊  | 284/363 [00:22<00:03, 23.64it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 31.05it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 29.78it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 30.99it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 28.62it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.11it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 25.76it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.43it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.07it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.74it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.77it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.34it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.50it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 18.76it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 25.53it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 25.85it/s]
                                                            
Job chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer completed after 204.73s with status: succeeded
Stopping job with name chaiml-ir-v4-dpo-irv0-l-29534-v1-mkmlizer
Pipeline stage MKMLizer completed in 205.51s
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-dpo-irv0-l-29534-v1
Waiting for inference service chaiml-ir-v4-dpo-irv0-l-29534-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', '')
Inference service chaiml-ir-v4-dpo-irv0-l-29534-v1 ready after 110.37494826316833s
Pipeline stage MKMLDeployer completed in 111.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7540342807769775s
Received healthy response to inference request in 2.2744147777557373s
Received healthy response to inference request in 2.135802745819092s
Received healthy response to inference request in 2.409653663635254s
Received healthy response to inference request in 2.3241755962371826s
5 requests
0 failed requests
5th percentile: 2.1635251522064207
10th percentile: 2.19124755859375
20th percentile: 2.2466923713684084
30th percentile: 2.2843669414520265
40th percentile: 2.3042712688446043
50th percentile: 2.3241755962371826
60th percentile: 2.358366823196411
70th percentile: 2.39255805015564
80th percentile: 2.4785297870635987
90th percentile: 2.616282033920288
95th percentile: 2.6851581573486327
99th percentile: 2.7402590560913085
mean time: 2.379616212844849
Pipeline stage StressChecker completed in 13.34s
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 0.74s
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 0.65s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv0-l_29534_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-dpo-irv0-l-29534-v1-profiler
Waiting for inference service chaiml-ir-v4-dpo-irv0-l-29534-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 3212.94s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv0-l_29534_v1 status is now inactive due to auto deactivation removed underperforming models