chaiml-ir-v4-1-dpo-irv0_48911

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-1-dpo-irv0_48911_v1

model_name: training123

model_group: ChaiML/ir-v4-1-dpo_irv0-

status: inactive

timestamp: 2025-10-29T15:02:59+00:00

num_battles: 5856

num_wins: 3061

celo_rating: 1301.39

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-1-dpo_irv0-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': 0.38142978293509067, 'latency_mean': 2.6215941596031187, 'latency_p50': 2.620940685272217, 'latency_p90': 2.8712286710739137}, {'batch_size': 2, 'throughput': 0.5682542696915013, 'latency_mean': 3.5123138773441314, 'latency_p50': 3.5284961462020874, 'latency_p90': 3.8316918134689333}, {'batch_size': 3, 'throughput': 0.7091264403842347, 'latency_mean': 4.227924571037293, 'latency_p50': 4.223244309425354, 'latency_p90': 4.566512989997864}, {'batch_size': 4, 'throughput': 0.8019357739461094, 'latency_mean': 4.975977628231049, 'latency_p50': 4.931919813156128, 'latency_p90': 5.602207541465759}, {'batch_size': 5, 'throughput': 0.8619429096748779, 'latency_mean': 5.7611243546009065, 'latency_p50': 5.782922387123108, 'latency_p90': 6.597979712486267}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-1-dpo_irv0-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-29

win_ratio: 0.5227117486338798

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': ['\n', 'You:', '</s>', '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-v4-1-dpo-irv0-48911-v1-mkmlizer
Waiting for job on chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer to finish
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-v4-1-dpo-irv0-48911-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: Downloaded to shared memory in 67.570s
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: Checking if ChaiML/ir-v4-1-dpo_irv0-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfo89ii8s, device:0
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: quantized model in 41.522s
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: Processed model ChaiML/ir-v4-1-dpo_irv0-lr5e6b01-cosine in 109.093s
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia/config.json
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia/tokenizer.json
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-48911-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.19it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 39.99it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:09, 34.99it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.34it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.61it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 26.35it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.74it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.48it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.26it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 34.19it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.93it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 29.64it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.60it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.76it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.10it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.47it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 27.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.38it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 33.43it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 28.86it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 31.27it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 30.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.67it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 34.70it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.72it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.13it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 33.65it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 40.23it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.13it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.16it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.40it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.51it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.40it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.47it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.40it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.38it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.44it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.46it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  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,  4.38it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:24,  5.72it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.04it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.69it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.44it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.49it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:06, 19.45it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.26it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 25.67it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.61it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 32.49it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.97it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.91it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 31.09it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 30.58it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.97it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.29it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.27it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.79it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.71it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:02, 24.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 30.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.87it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.37it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.02it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.19it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.26it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.70it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.00it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.54it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.53it/s]
                                                            
Job chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer completed after 184.44s with status: succeeded
Stopping job with name chaiml-ir-v4-1-dpo-irv0-48911-v1-mkmlizer
Pipeline stage MKMLizer completed in 184.97s
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-v4-1-dpo-irv0-48911-v1
Waiting for inference service chaiml-ir-v4-1-dpo-irv0-48911-v1 to be ready
Inference service chaiml-ir-v4-1-dpo-irv0-48911-v1 ready after 110.39505624771118s
Pipeline stage MKMLDeployer completed in 111.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5765137672424316s
Received healthy response to inference request in 2.43595027923584s
Received healthy response to inference request in 2.62309193611145s
Received healthy response to inference request in 2.4995334148406982s
Received healthy response to inference request in 2.6214990615844727s
5 requests
0 failed requests
5th percentile: 2.4486669063568116
10th percentile: 2.4613835334777834
20th percentile: 2.4868167877197265
30th percentile: 2.514929485321045
40th percentile: 2.5457216262817384
50th percentile: 2.5765137672424316
60th percentile: 2.5945078849792482
70th percentile: 2.6125020027160644
80th percentile: 2.621817636489868
90th percentile: 2.622454786300659
95th percentile: 2.622773361206055
99th percentile: 2.623028221130371
mean time: 2.5513176918029785
Pipeline stage StressChecker completed in 14.28s
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 0.71s
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 0.79s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-irv0_48911_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-1-dpo-irv0-48911-v1-profiler
Waiting for inference service chaiml-ir-v4-1-dpo-irv0-48911-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 5008.56s
Shutdown handler de-registered