chaiml-ir-v4-2-dpo-irv0_95038

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-2-dpo-irv0_95038_v1

model_name: training123

model_group: ChaiML/ir-v4-2-dpo_irv0-

status: inactive

timestamp: 2025-11-01T22:43:17+00:00

num_battles: 5917

num_wins: 3090

celo_rating: 1304.39

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-2-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': 0.3828647547673142, 'latency_mean': 2.6117920780181887, 'latency_p50': 2.6128368377685547, 'latency_p90': 2.885683369636536}, {'batch_size': 2, 'throughput': 0.5701107800864592, 'latency_mean': 3.49818088054657, 'latency_p50': 3.5135674476623535, 'latency_p90': 3.8703461647033692}, {'batch_size': 3, 'throughput': 0.7030170714081245, 'latency_mean': 4.255941544771194, 'latency_p50': 4.256565809249878, 'latency_p90': 4.700588703155518}, {'batch_size': 4, 'throughput': 0.797167986407359, 'latency_mean': 5.013798432350159, 'latency_p50': 5.004255175590515, 'latency_p90': 5.506698131561279}, {'batch_size': 5, 'throughput': 0.8564741454071687, 'latency_mean': 5.814052172899246, 'latency_p50': 5.756513714790344, 'latency_p90': 6.72580738067627}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-2-dpo_irv0-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-11-01

win_ratio: 0.5222241000507014

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:', '\n', 'You:', '</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-v4-2-dpo-irv0-95038-v1-mkmlizer
Waiting for job on chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer to finish
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: Downloaded to shared memory in 66.688s
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: Checking if ChaiML/ir-v4-2-dpo_irv0-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf6yj0mix, device:0
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: quantized model in 41.748s
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: Processed model ChaiML/ir-v4-2-dpo_irv0-lr5e6b01-cosine in 108.437s
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia/config.json
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia/tokenizer.json
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-irv0-95038-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.37it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.75it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.52it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.14it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.23it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.83it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.38it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.88it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.77it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.12it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.74it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.27it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.15it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.27it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.36it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:10, 26.63it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:09, 27.11it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 31.44it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 26.87it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.98it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 30.95it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 32.13it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 32.74it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.37it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.89it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.33it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.67it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.43it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.24it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.44it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.78it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.35it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.47it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.63it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.38it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.54it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.60it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.63it/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,  2.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:43,  3.46it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.87it/s]
Loading 0:  61%|██████    | 221/363 [00:19<00:23,  6.17it/s]
Loading 0:  62%|██████▏   | 224/363 [00:19<00:18,  7.41it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.80it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.62it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.26it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 19.59it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:04, 24.42it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 25.31it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:03, 29.79it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:03, 29.16it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.36it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.50it/s]
Loading 0:  77%|███████▋  | 280/363 [00:21<00:02, 28.31it/s]
Loading 0:  78%|███████▊  | 284/363 [00:21<00:03, 25.99it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.63it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.93it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.94it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 29.90it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 29.17it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 25.58it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 31.20it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.74it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.01it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.47it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.50it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.13it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 20.64it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.23it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.82it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.10it/s]
                                                            
Job chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer completed after 196.42s with status: succeeded
Stopping job with name chaiml-ir-v4-2-dpo-irv0-95038-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.43s
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-irv0-95038-v1
Waiting for inference service chaiml-ir-v4-2-dpo-irv0-95038-v1 to be ready
Inference service chaiml-ir-v4-2-dpo-irv0-95038-v1 ready after 130.67789363861084s
Pipeline stage MKMLDeployer completed in 131.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7781782150268555s
Received healthy response to inference request in 2.2198257446289062s
Received healthy response to inference request in 2.2762584686279297s
Received healthy response to inference request in 2.4513347148895264s
Received healthy response to inference request in 2.138733148574829s
5 requests
0 failed requests
5th percentile: 2.1549516677856446
10th percentile: 2.17117018699646
20th percentile: 2.2036072254180907
30th percentile: 2.2311122894287108
40th percentile: 2.2536853790283202
50th percentile: 2.2762584686279297
60th percentile: 2.346288967132568
70th percentile: 2.416319465637207
80th percentile: 2.5167034149169925
90th percentile: 2.6474408149719237
95th percentile: 2.7128095149993894
99th percentile: 2.7651044750213623
mean time: 2.3728660583496093
Pipeline stage StressChecker completed in 13.54s
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 0.72s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-irv0_95038_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5696.17s
Shutdown handler de-registered