chaiml-ir-v3-2-dpo-irv13-lr15

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-2-dpo-irv13-lr15_v1

model_name: training123

model_group: ChaiML/ir-v3-2-dpo_irv13

status: torndown

timestamp: 2025-11-17T22:01:28+00:00

num_battles: 7353

num_wins: 3914

celo_rating: 1305.23

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v3-2-dpo_irv13-lr15

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': 0.36884712096789724, 'latency_mean': 2.71102774143219, 'latency_p50': 2.726544737815857, 'latency_p90': 2.9556963443756104}, {'batch_size': 2, 'throughput': 0.5432080733358097, 'latency_mean': 3.6743186151981355, 'latency_p50': 3.6729384660720825, 'latency_p90': 4.002341198921203}, {'batch_size': 3, 'throughput': 0.6609494246648597, 'latency_mean': 4.53645733833313, 'latency_p50': 4.571376204490662, 'latency_p90': 5.004135775566101}, {'batch_size': 4, 'throughput': 0.7472083340861957, 'latency_mean': 5.33685265660286, 'latency_p50': 5.374200463294983, 'latency_p90': 6.061634540557861}, {'batch_size': 5, 'throughput': 0.8044747936041405, 'latency_mean': 6.1825750386714935, 'latency_p50': 6.190159201622009, 'latency_p90': 7.082217979431152}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-2-dpo_irv13-lr15

model_size: 24B

ranking_group: single

throughput_3p7s: 0.55

us_pacific_date: 2025-11-14

win_ratio: 0.5322997416020672

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:', '</s>', '\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-v3-2-dpo-irv13-lr15-v1-mkmlizer
Waiting for job on chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer to finish
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-ir-v3-4-dpo-irv13_v3: ('http://chaiml-ir-v3-4-dpo-irv13-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39108->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: Downloaded to shared memory in 71.820s
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: Checking if ChaiML/ir-v3-2-dpo_irv13-lr15 already exists in ChaiML
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt0553i3q, device:0
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: quantized model in 41.290s
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: Processed model ChaiML/ir-v3-2-dpo_irv13-lr15 in 113.111s
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia/config.json
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia/tokenizer.json
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-2-dpo-irv13-lr15-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.65it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.39it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.81it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.21it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.18it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.44it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.56it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.47it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.04it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.17it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.38it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 30.95it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.94it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 33.19it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.65it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:09, 28.15it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 35.75it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 34.22it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:08, 30.07it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:07, 32.50it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 32.93it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 34.25it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 32.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.87it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 33.16it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.33it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 34.20it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 41.01it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 28.43it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 26.20it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.34it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 32.05it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.15it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.54it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.44it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 29.86it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:18<02:11,  1.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.12it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:52,  2.85it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:32,  4.45it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:24,  5.79it/s]
Loading 0:  62%|██████▏   | 226/363 [00:19<00:19,  7.13it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.59it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.60it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 19.55it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:05, 21.02it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:04, 25.29it/s]
Loading 0:  71%|███████▏  | 259/363 [00:20<00:04, 25.78it/s]
Loading 0:  73%|███████▎  | 266/363 [00:20<00:02, 32.80it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.14it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.28it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 30.64it/s]
Loading 0:  79%|███████▉  | 286/363 [00:21<00:02, 30.48it/s]
Loading 0:  80%|████████  | 291/363 [00:21<00:02, 33.92it/s]
Loading 0:  81%|████████▏ | 295/363 [00:21<00:02, 32.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.87it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 32.12it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 31.35it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 27.63it/s]
Loading 0:  88%|████████▊ | 318/363 [00:22<00:01, 32.97it/s]
Loading 0:  89%|████████▊ | 322/363 [00:22<00:01, 31.89it/s]
Loading 0:  90%|█████████ | 327/363 [00:22<00:01, 35.04it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.50it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.41it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.07it/s]
Loading 0:  94%|█████████▍| 343/363 [00:23<00:00, 20.58it/s]
Loading 0:  96%|█████████▌| 348/363 [00:23<00:00, 22.19it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.85it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.32it/s]
                                                            
Job chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer completed after 186.75s with status: succeeded
Stopping job with name chaiml-ir-v3-2-dpo-irv13-lr15-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.38s
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-v3-2-dpo-irv13-lr15-v1
Waiting for inference service chaiml-ir-v3-2-dpo-irv13-lr15-v1 to be ready
Inference service chaiml-ir-v3-2-dpo-irv13-lr15-v1 ready after 160.86777663230896s
Pipeline stage MKMLDeployer completed in 161.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8313138484954834s
Received healthy response to inference request in 2.545499801635742s
Received healthy response to inference request in 2.567007303237915s
Received healthy response to inference request in 2.2565159797668457s
Received healthy response to inference request in 2.302873134613037s
5 requests
0 failed requests
5th percentile: 2.265787410736084
10th percentile: 2.2750588417053224
20th percentile: 2.293601703643799
30th percentile: 2.351398468017578
40th percentile: 2.44844913482666
50th percentile: 2.545499801635742
60th percentile: 2.5541028022766112
70th percentile: 2.5627058029174803
80th percentile: 2.619868612289429
90th percentile: 2.725591230392456
95th percentile: 2.7784525394439696
99th percentile: 2.820741586685181
mean time: 2.500642013549805
Pipeline stage StressChecker completed in 13.92s
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 0.68s
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 0.63s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-irv13-lr15_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v3-2-dpo-irv13-lr15-v1-profiler
Waiting for inference service chaiml-ir-v3-2-dpo-irv13-lr15-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 5951.16s
Shutdown handler de-registered
chaiml-ir-v3-2-dpo-irv13-lr15_v1 status is now torndown due to DeploymentManager action