chaiml-ir-v4-1-dpo-irv0_40057

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-1-dpo-irv0_40057_v1

model_name: training123

model_group: ChaiML/ir-v4-1-dpo_irv0-

status: inactive

timestamp: 2025-10-29T14:39:45+00:00

num_battles: 6512

num_wins: 3422

celo_rating: 1302.61

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-1-dpo_irv0-lr5e6b01

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': 0.37973502251565205, 'latency_mean': 2.633314483165741, 'latency_p50': 2.651626944541931, 'latency_p90': 2.88516526222229}, {'batch_size': 2, 'throughput': 0.5654739304039731, 'latency_mean': 3.532912051677704, 'latency_p50': 3.5432398319244385, 'latency_p90': 3.865212345123291}, {'batch_size': 3, 'throughput': 0.6967658257837366, 'latency_mean': 4.296486691236496, 'latency_p50': 4.320827007293701, 'latency_p90': 4.681049776077271}, {'batch_size': 4, 'throughput': 0.7924176717473996, 'latency_mean': 5.035796818733215, 'latency_p50': 5.0619542598724365, 'latency_p90': 5.641826009750366}, {'batch_size': 5, 'throughput': 0.849176665213976, 'latency_mean': 5.863450083732605, 'latency_p50': 5.861293077468872, 'latency_p90': 6.722271943092346}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-1-dpo_irv0-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-10-29

win_ratio: 0.5254914004914005

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>', 'User:', '\n', '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
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer
Waiting for job on chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer to finish
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: Downloaded to shared memory in 65.430s
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: Checking if ChaiML/ir-v4-1-dpo_irv0-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9yyepfbm, device:0
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: quantized model in 42.050s
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: Processed model ChaiML/ir-v4-1-dpo_irv0-lr5e6b01 in 107.481s
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia/config.json
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia/tokenizer.json
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv0-40057-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.25it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.03it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.75it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.04it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.44it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.80it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.04it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.23it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.55it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.84it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.80it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 33.11it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 29.19it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 26.41it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.14it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.63it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 26.49it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 26.26it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.65it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.64it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 26.77it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.51it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.51it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 32.26it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.09it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 34.63it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.95it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.17it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.75it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.24it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 26.55it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.75it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.95it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.01it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.25it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.08it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 29.11it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.25it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 24.06it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:10,  1.24it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:51,  1.43it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.15it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:56,  2.71it/s]
Loading 0:  59%|█████▉    | 214/363 [00:19<00:42,  3.50it/s]
Loading 0:  60%|██████    | 218/363 [00:19<00:29,  4.91it/s]
Loading 0:  61%|██████    | 222/363 [00:19<00:21,  6.66it/s]
Loading 0:  62%|██████▏   | 225/363 [00:20<00:18,  7.59it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:12, 10.32it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 15.98it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:06, 17.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 22.07it/s]
Loading 0:  69%|██████▉   | 250/363 [00:20<00:04, 23.22it/s]
Loading 0:  70%|███████   | 255/363 [00:20<00:03, 27.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.56it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.45it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 24.88it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.87it/s]
Loading 0:  78%|███████▊  | 282/363 [00:21<00:02, 30.96it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.53it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.83it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.19it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.08it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 30.43it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 28.62it/s]
Loading 0:  86%|████████▌ | 312/363 [00:22<00:01, 25.52it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.32it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.49it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 33.35it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:01, 31.26it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.43it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.24it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 20.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.63it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 28.94it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.61it/s]
                                                            
Job chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer completed after 189.54s with status: succeeded
Stopping job with name chaiml-ir-v4-1-dpo-irv0-40057-v1-mkmlizer
Pipeline stage MKMLizer completed in 190.31s
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-v4-1-dpo-irv0-40057-v1
Waiting for inference service chaiml-ir-v4-1-dpo-irv0-40057-v1 to be ready
Inference service chaiml-ir-v4-1-dpo-irv0-40057-v1 ready after 100.34100222587585s
Pipeline stage MKMLDeployer completed in 100.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0796711444854736s
Received healthy response to inference request in 2.390932083129883s
Received healthy response to inference request in 2.3276307582855225s
Received healthy response to inference request in 2.1156206130981445s
Received healthy response to inference request in 2.9001362323760986s
5 requests
0 failed requests
5th percentile: 2.15802264213562
10th percentile: 2.2004246711730957
20th percentile: 2.285228729248047
30th percentile: 2.3402910232543945
40th percentile: 2.3656115531921387
50th percentile: 2.390932083129883
60th percentile: 2.5946137428283693
70th percentile: 2.7982954025268554
80th percentile: 2.936043214797974
90th percentile: 3.0078571796417237
95th percentile: 3.0437641620635985
99th percentile: 3.0724897480010984
mean time: 2.5627981662750243
Pipeline stage StressChecker completed in 13.97s
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 0.92s
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 0.59s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-irv0_40057_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4995.16s
Shutdown handler de-registered