chaiml-ir-v4-2-dpo-ir31_43357

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-2-dpo-ir31_43357_v1

model_name: training123

model_group: ChaiML/ir-v4-2-dpo_ir31-

status: torndown

timestamp: 2025-11-07T08:31:15+00:00

num_battles: 6044

num_wins: 3224

celo_rating: 1314.75

family_friendly_score: 0.4366

family_friendly_standard_error: 0.007013992301107837

submission_type: basic

model_repo: ChaiML/ir-v4-2-dpo_ir31-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': 0.3774350533141105, 'latency_mean': 2.649342577457428, 'latency_p50': 2.656033754348755, 'latency_p90': 2.8916748285293576}, {'batch_size': 2, 'throughput': 0.5658464851126911, 'latency_mean': 3.525936335325241, 'latency_p50': 3.5336508750915527, 'latency_p90': 3.842191743850708}, {'batch_size': 3, 'throughput': 0.6999892741177897, 'latency_mean': 4.267266139984131, 'latency_p50': 4.262864947319031, 'latency_p90': 4.633572936058044}, {'batch_size': 4, 'throughput': 0.7937264344830042, 'latency_mean': 5.032216708660126, 'latency_p50': 4.995354056358337, 'latency_p90': 5.776644372940063}, {'batch_size': 5, 'throughput': 0.8518002246363794, 'latency_mean': 5.841116219758987, 'latency_p50': 5.880521059036255, 'latency_p90': 6.7237921237945555}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-2-dpo_ir31-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-11-04

win_ratio: 0.5334215751158173

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', '</s>', 'User:', 'You:'], '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer
Waiting for job on chaiml-ir-v4-2-dpo-ir31-43357-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-v4-2-dpo-ir31-43357-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: Downloaded to shared memory in 57.771s
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: Checking if ChaiML/ir-v4-2-dpo_ir31-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6mlvya3l, device:0
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: quantized model in 42.202s
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: Processed model ChaiML/ir-v4-2-dpo_ir31-lr5e6b01-cosine in 99.973s
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia/config.json
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia/tokenizer.json
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-2-dpo-ir31-43357-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.58it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.58it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 42.05it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.50it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.32it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:11, 28.32it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:12, 25.91it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.11it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 32.28it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:09, 33.06it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:09, 33.30it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.68it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.86it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 26.10it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.31it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.14it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 28.01it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 26.66it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.97it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.59it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.95it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.58it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.17it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:07, 31.45it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:11, 20.47it/s]
Loading 0:  36%|███▌      | 131/363 [00:04<00:13, 16.75it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:09, 24.48it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 25.14it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 32.37it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 23.30it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 23.84it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 30.87it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.45it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.83it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.66it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.53it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.12it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.25it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.56it/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%|█████▊    | 212/363 [00:19<00:53,  2.84it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:32,  4.43it/s]
Loading 0:  61%|██████    | 222/363 [00:20<00:24,  5.79it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:15,  8.76it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:09, 13.57it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 15.65it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 19.61it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 20.97it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 24.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:04, 25.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 32.97it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.09it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.93it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.04it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.36it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.75it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.31it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.16it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 29.97it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.83it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.69it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.29it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.85it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.09it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 30.71it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 31.71it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 32.14it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.43it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.14it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 28.61it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.63it/s]
                                                            
Job chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer completed after 184.62s with status: succeeded
Stopping job with name chaiml-ir-v4-2-dpo-ir31-43357-v1-mkmlizer
Pipeline stage MKMLizer completed in 185.48s
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-v4-2-dpo-ir31-43357-v1
Waiting for inference service chaiml-ir-v4-2-dpo-ir31-43357-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-v4-2-dpo-ir31-43357-v1 ready after 140.56398940086365s
Pipeline stage MKMLDeployer completed in 141.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5939252376556396s
Received healthy response to inference request in 2.129042387008667s
Received healthy response to inference request in 2.3446433544158936s
Received healthy response to inference request in 2.1393184661865234s
Received healthy response to inference request in 2.297516107559204s
5 requests
0 failed requests
5th percentile: 2.131097602844238
10th percentile: 2.1331528186798097
20th percentile: 2.1372632503509523
30th percentile: 2.1709579944610597
40th percentile: 2.234237051010132
50th percentile: 2.297516107559204
60th percentile: 2.31636700630188
70th percentile: 2.335217905044556
80th percentile: 2.394499731063843
90th percentile: 2.4942124843597413
95th percentile: 2.5440688610076903
99th percentile: 2.5839539623260497
mean time: 2.3008891105651856
Pipeline stage StressChecker completed in 12.98s
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 0.89s
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 0.69s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-ir31_43357_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ir-v4-2-dpo-ir31-43357-v1-profiler
Waiting for inference service chaiml-ir-v4-2-dpo-ir31-43357-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 3149.09s
Shutdown handler de-registered
chaiml-ir-v4-2-dpo-ir31_43357_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v4-2-dpo-ir31_43357_v1 status is now torndown due to DeploymentManager action