developer_uid: chai_backend_admin
submission_id: chaiml-ir-v4-1-dpo-ir31_54831_v1
model_name: training123
model_group: ChaiML/ir-v4-1-dpo_ir31-
status: torndown
timestamp: 2025-11-07T10:21:19+00:00
num_battles: 6959
num_wins: 3541
celo_rating: 1294.99
family_friendly_score: 0.42679999999999996
family_friendly_standard_error: 0.00699488041355962
submission_type: basic
model_repo: ChaiML/ir-v4-1-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': 0.387021326965064, 'latency_mean': 2.5837362039089204, 'latency_p50': 2.5750497579574585, 'latency_p90': 2.851614212989807}, {'batch_size': 2, 'throughput': 0.5785223193095869, 'latency_mean': 3.449329069852829, 'latency_p50': 3.4602091312408447, 'latency_p90': 3.7848045110702513}, {'batch_size': 3, 'throughput': 0.7157140396264956, 'latency_mean': 4.177311463356018, 'latency_p50': 4.181959748268127, 'latency_p90': 4.582074451446533}, {'batch_size': 4, 'throughput': 0.8099956359482093, 'latency_mean': 4.909297922849655, 'latency_p50': 4.909061789512634, 'latency_p90': 5.643661665916443}, {'batch_size': 5, 'throughput': 0.877991741761111, 'latency_mean': 5.668157312870026, 'latency_p50': 5.654884338378906, 'latency_p90': 6.605210685729981}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ir-v4-1-dpo_ir31-lr5e6b01-cosine
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-11-04
win_ratio: 0.5088374766489439
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', 'User:', '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-v4-1-dpo-ir31-54831-v1-mkmlizer
Waiting for job on chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer to finish
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: Downloaded to shared memory in 84.684s
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: Checking if ChaiML/ir-v4-1-dpo_ir31-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnsj3ihza, device:0
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: quantized model in 43.446s
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: Processed model ChaiML/ir-v4-1-dpo_ir31-lr5e6b01-cosine in 128.131s
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia/config.json
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia/tokenizer.json
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-ir31-54831-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.90it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 40.27it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.00it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.26it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.23it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 41.32it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.55it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 23.76it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.37it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.96it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.26it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.12it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.36it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 27.38it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:12, 23.38it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 25.93it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:13, 20.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.18it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:11, 24.80it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 23.45it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 29.15it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 25.62it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 28.53it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 29.53it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.70it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.00it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.49it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.74it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.07it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 31.82it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.26it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.58it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.79it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.62it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.92it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.06it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 30.92it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 31.92it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 29.02it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.30it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.80it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.09it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:43,  3.39it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.76it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.03it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:19,  7.20it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.49it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.38it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.71it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.88it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.56it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.03it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.21it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.27it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 34.33it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:04, 22.87it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.52it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.41it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.36it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 32.59it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 30.93it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 31.91it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 29.07it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.46it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 25.71it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.10it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 29.75it/s]
Loading 0:  90%|████████▉ | 326/363 [00:24<00:01, 28.68it/s]
Loading 0:  91%|█████████ | 329/363 [00:24<00:01, 24.22it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 30.50it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 31.86it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.93it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.19it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.47it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 25.96it/s]
Loading 0: 100%|██████████| 363/363 [00:25<00:00, 24.25it/s]
                                                            

Job chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer completed after 194.55s with status: succeeded
Stopping job with name chaiml-ir-v4-1-dpo-ir31-54831-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.05s
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-v4-1-dpo-ir31-54831-v1
Waiting for inference service chaiml-ir-v4-1-dpo-ir31-54831-v1 to be ready
Inference service chaiml-ir-v4-1-dpo-ir31-54831-v1 ready after 140.61023688316345s
Pipeline stage MKMLDeployer completed in 141.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.484665870666504s
Received healthy response to inference request in 2.1705739498138428s
Received healthy response to inference request in 2.5904386043548584s
Received healthy response to inference request in 2.283153533935547s
Received healthy response to inference request in 2.4673657417297363s
5 requests
0 failed requests
5th percentile: 2.1930898666381835
10th percentile: 2.2156057834625242
20th percentile: 2.260637617111206
30th percentile: 2.319995975494385
40th percentile: 2.3936808586120604
50th percentile: 2.4673657417297363
60th percentile: 2.4742857933044435
70th percentile: 2.4812058448791503
80th percentile: 2.5058204174041747
90th percentile: 2.548129510879517
95th percentile: 2.5692840576171876
99th percentile: 2.586207695007324
mean time: 2.3992395401000977
Pipeline stage StressChecker completed in 13.48s
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 0.70s
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 0.71s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-ir31_54831_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3122.67s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-ir31_54831_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v4-1-dpo-ir31_54831_v1 status is now torndown due to DeploymentManager action