chaiml-ir-v3-3-dpo-irv13

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v3-3-dpo-irv13_v1

model_name: training123

model_group: ChaiML/ir-v3-3-dpo_irv13

status: torndown

timestamp: 2025-11-17T11:51:27+00:00

num_battles: 5709

num_wins: 2956

celo_rating: 1294.67

family_friendly_score: 0.44099999999999995

family_friendly_standard_error: 0.007021666468866205

submission_type: basic

model_repo: ChaiML/ir-v3-3-dpo_irv13

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': 0.38417984624226387, 'latency_mean': 2.602841682434082, 'latency_p50': 2.60249662399292, 'latency_p90': 2.849410343170166}, {'batch_size': 2, 'throughput': 0.5721235906059006, 'latency_mean': 3.4857666552066804, 'latency_p50': 3.493127942085266, 'latency_p90': 3.79144606590271}, {'batch_size': 3, 'throughput': 0.7143257398309959, 'latency_mean': 4.192191188335419, 'latency_p50': 4.1948771476745605, 'latency_p90': 4.530481362342835}, {'batch_size': 4, 'throughput': 0.8164118085692933, 'latency_mean': 4.876570791006088, 'latency_p50': 4.888123869895935, 'latency_p90': 5.430266427993774}, {'batch_size': 5, 'throughput': 0.8826449973482533, 'latency_mean': 5.6500518453121185, 'latency_p50': 5.64836323261261, 'latency_p90': 6.445863437652588}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v3-3-dpo_irv13

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-14

win_ratio: 0.5177789455246102

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': ['</s>', 'You:', '\n', '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-v3-3-dpo-irv13-v1-mkmlizer
Waiting for job on chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer to finish
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: Downloaded to shared memory in 62.881s
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: Checking if ChaiML/ir-v3-3-dpo_irv13 already exists in ChaiML
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzfbiw_tk, device:0
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: quantized model in 42.197s
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: Processed model ChaiML/ir-v3-3-dpo_irv13 in 105.079s
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia/config.json
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia/special_tokens_map.json
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia/tokenizer_config.json
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia/tokenizer.json
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v3-3-dpo-irv13-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.93it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 40.24it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.75it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.35it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.86it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.01it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.93it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.30it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.78it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.56it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.01it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.92it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.29it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.76it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 26.04it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.81it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.95it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.23it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.69it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.83it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.37it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.94it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.64it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 31.72it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.10it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.64it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.97it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.35it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.84it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.98it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.15it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.11it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.02it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.58it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.08it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.97it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.82it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.04it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.83it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:15,  1.20it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.40it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.78it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.26it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.60it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.51it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.12it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 19.33it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 24.16it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 25.38it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.84it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.66it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.75it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.55it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.85it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.89it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.71it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 34.01it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:02, 30.01it/s]
Loading 0:  83%|████████▎ | 303/363 [00:22<00:01, 32.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:23<00:02, 21.13it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 20.81it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 28.47it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 28.12it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 31.91it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.09it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.07it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 33.18it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.47it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.05it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.60it/s]
                                                            
Job chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer completed after 175.44s with status: succeeded
Stopping job with name chaiml-ir-v3-3-dpo-irv13-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.94s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v3-3-dpo-irv13-v1
Waiting for inference service chaiml-ir-v3-3-dpo-irv13-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-v3-3-dpo-irv13-v1 ready after 150.62444806098938s
Pipeline stage MKMLDeployer completed in 151.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8471198081970215s
Received healthy response to inference request in 2.4741106033325195s
Received healthy response to inference request in 2.20035719871521s
Received healthy response to inference request in 2.2912521362304688s
Received healthy response to inference request in 2.4419918060302734s
5 requests
0 failed requests
5th percentile: 2.2185361862182615
10th percentile: 2.2367151737213136
20th percentile: 2.273073148727417
30th percentile: 2.3214000701904296
40th percentile: 2.3816959381103517
50th percentile: 2.4419918060302734
60th percentile: 2.454839324951172
70th percentile: 2.4676868438720705
80th percentile: 2.54871244430542
90th percentile: 2.697916126251221
95th percentile: 2.772517967224121
99th percentile: 2.8321994400024413
mean time: 2.450966310501099
Pipeline stage StressChecker completed in 13.90s
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 1.09s
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 0.66s
Shutdown handler de-registered
chaiml-ir-v3-3-dpo-irv13_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 0.11s
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-v3-3-dpo-irv13-v1-profiler
Waiting for inference service chaiml-ir-v3-3-dpo-irv13-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 3058.12s
Shutdown handler de-registered
chaiml-ir-v3-3-dpo-irv13_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v3-3-dpo-irv13_v1 status is now torndown due to DeploymentManager action