chaiml-ir-v4-dpo-irv0-l_45042

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-dpo-irv0-l_45042_v1

model_name: training123

model_group: ChaiML/ir-v4-dpo_irv0-lr

status: inactive

timestamp: 2025-10-29T21:16:47+00:00

num_battles: 5955

num_wins: 3093

celo_rating: 1290.81

family_friendly_score: 0.46719999999999995

family_friendly_standard_error: 0.007055836732804976

submission_type: basic

model_repo: ChaiML/ir-v4-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': 0.3792536538894317, 'latency_mean': 2.636662746667862, 'latency_p50': 2.608006000518799, 'latency_p90': 2.9007004499435425}, {'batch_size': 2, 'throughput': 0.5717915795982592, 'latency_mean': 3.4964636957645414, 'latency_p50': 3.4849464893341064, 'latency_p90': 3.845643424987793}, {'batch_size': 3, 'throughput': 0.7032393053051874, 'latency_mean': 4.262698533535004, 'latency_p50': 4.2574303150177, 'latency_p90': 5.001355290412903}, {'batch_size': 4, 'throughput': 0.7972997032336353, 'latency_mean': 4.987573547363281, 'latency_p50': 5.007993221282959, 'latency_p90': 5.6793797492980955}, {'batch_size': 5, 'throughput': 0.8564895614926287, 'latency_mean': 5.811574280261993, 'latency_p50': 5.857125997543335, 'latency_p90': 6.612221646308899}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

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

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-29

win_ratio: 0.5193954659949622

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-dpo-irv0-l-45042-v1-mkmlizer
Waiting for job on chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer to finish
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-dpo-irv0-l-45042-v1-mkmlizer: Downloaded to shared memory in 62.389s
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: Checking if ChaiML/ir-v4-dpo_irv0-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpewkri7a8, device:0
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: quantized model in 41.965s
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: Processed model ChaiML/ir-v4-dpo_irv0-lr5e6b01-cosine in 104.354s
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-45042-v1/nvidia
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-45042-v1/nvidia/tokenizer.json
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-45042-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv0-l-45042-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.88it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.80it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.78it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.78it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.98it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 27.96it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.81it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.95it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.80it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.23it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:08, 33.46it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:08, 34.46it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.64it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.75it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.83it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.39it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.40it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.79it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.24it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.14it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.55it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.17it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.84it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.72it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 30.94it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.40it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.16it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.67it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.31it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.83it/s]
Loading 0:  42%|████▏     | 153/363 [00:04<00:08, 25.12it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.22it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.97it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.77it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.84it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.76it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.68it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.38it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.82it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.15it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.67it/s]
Loading 0:  59%|█████▉    | 215/363 [00:19<00:39,  3.72it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:30,  4.74it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.04it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.25it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.62it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.50it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.05it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 18.26it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 23.06it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.39it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.85it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.59it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.82it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.70it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 24.25it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.18it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.19it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.03it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.57it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:02, 28.74it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:02, 26.82it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 21.40it/s]
Loading 0:  87%|████████▋ | 316/363 [00:23<00:01, 26.17it/s]
Loading 0:  88%|████████▊ | 320/363 [00:23<00:01, 23.55it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 31.37it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 30.76it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.86it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.49it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.48it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.05it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.47it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.87it/s]
                                                            
Job chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer completed after 156.5s with status: succeeded
Stopping job with name chaiml-ir-v4-dpo-irv0-l-45042-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-dpo-irv0-l-45042-v1
Waiting for inference service chaiml-ir-v4-dpo-irv0-l-45042-v1 to be ready
Inference service chaiml-ir-v4-dpo-irv0-l-45042-v1 ready after 110.73963475227356s
Pipeline stage MKMLDeployer completed in 111.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5514063835144043s
Received healthy response to inference request in 2.4402618408203125s
Received healthy response to inference request in 2.1361050605773926s
Received healthy response to inference request in 2.2052812576293945s
Received healthy response to inference request in 2.5918984413146973s
5 requests
0 failed requests
5th percentile: 2.149940299987793
10th percentile: 2.1637755393981934
20th percentile: 2.1914460182189943
30th percentile: 2.252277374267578
40th percentile: 2.3462696075439453
50th percentile: 2.4402618408203125
60th percentile: 2.484719657897949
70th percentile: 2.5291774749755858
80th percentile: 2.5595047950744627
90th percentile: 2.57570161819458
95th percentile: 2.583800029754639
99th percentile: 2.5902787590026857
mean time: 2.38499059677124
Pipeline stage StressChecker completed in 13.22s
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 0.65s
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 0.60s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv0-l_45042_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-dpo-irv0-l-45042-v1-profiler
Waiting for inference service chaiml-ir-v4-dpo-irv0-l-45042-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 3264.10s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv0-l_45042_v1 status is now inactive due to auto deactivation removed underperforming models