chaiml-ir-v4-dpo-irv13-_89808

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-dpo-irv13-_89808_v1

model_name: training123

model_group: ChaiML/ir-v4-dpo_irv13-l

status: inactive

timestamp: 2025-10-29T17:36:42+00:00

num_battles: 6146

num_wins: 3087

celo_rating: 1294.81

family_friendly_score: 0.479

family_friendly_standard_error: 0.007064828377250222

submission_type: basic

model_repo: ChaiML/ir-v4-dpo_irv13-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': 0.38111379526783074, 'latency_mean': 2.6237906408309937, 'latency_p50': 2.6274548768997192, 'latency_p90': 2.8625256538391115}, {'batch_size': 2, 'throughput': 0.5675379859832405, 'latency_mean': 3.5118598175048827, 'latency_p50': 3.530812978744507, 'latency_p90': 3.7824954271316527}, {'batch_size': 3, 'throughput': 0.7007267004089788, 'latency_mean': 4.266489380598069, 'latency_p50': 4.284508466720581, 'latency_p90': 4.605470418930054}, {'batch_size': 4, 'throughput': 0.7953946264572357, 'latency_mean': 5.0155766689777375, 'latency_p50': 5.017099380493164, 'latency_p90': 5.565877294540405}, {'batch_size': 5, 'throughput': 0.8666034015588076, 'latency_mean': 5.739195511341095, 'latency_p50': 5.748947024345398, 'latency_p90': 6.585843324661255}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-dpo_irv13-lr5e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.61

us_pacific_date: 2025-10-29

win_ratio: 0.5022779043280182

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>', '\n', '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
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer
Waiting for job on chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer to finish
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: Downloaded to shared memory in 58.298s
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: Checking if ChaiML/ir-v4-dpo_irv13-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfm93wh82, device:0
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: quantized model in 43.059s
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: Processed model ChaiML/ir-v4-dpo_irv13-lr5e6b01 in 101.357s
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia/config.json
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia/special_tokens_map.json
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia/tokenizer.json
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-89808-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.99it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.53it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 40.76it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.73it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 43.62it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.07it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:12, 25.45it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 25.95it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:15, 20.38it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:14, 21.71it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:14, 21.04it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:16, 18.46it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:14, 21.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.21it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.11it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.52it/s]
Loading 0:  23%|██▎       | 83/363 [00:03<00:09, 28.30it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 25.74it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:10, 25.69it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.06it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.93it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 26.87it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.45it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.23it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.23it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.73it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.87it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.98it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:06, 32.70it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 39.06it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 25.11it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.39it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.43it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.35it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.51it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.88it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 32.35it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.57it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 28.81it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.03it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 26.03it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<02:16,  1.19it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:56,  1.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:14,  2.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:58,  2.62it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.37it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.75it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.03it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:19,  7.25it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:12, 10.55it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:10, 12.45it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 17.02it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 23.86it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.60it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.00it/s]
Loading 0:  71%|███████▏  | 259/363 [00:22<00:03, 28.83it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 35.69it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:04, 22.76it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 22.01it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 28.87it/s]
Loading 0:  79%|███████▉  | 286/363 [00:23<00:02, 28.53it/s]
Loading 0:  80%|████████  | 291/363 [00:23<00:02, 31.77it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 30.55it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:02, 31.64it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 28.89it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.20it/s]
Loading 0:  86%|████████▌ | 311/363 [00:24<00:02, 23.67it/s]
Loading 0:  87%|████████▋ | 316/363 [00:24<00:01, 25.46it/s]
Loading 0:  88%|████████▊ | 320/363 [00:24<00:01, 23.58it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 31.36it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 29.90it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 31.22it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.40it/s]
Loading 0:  94%|█████████▍| 343/363 [00:25<00:01, 19.88it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.49it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.74it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.31it/s]
                                                            
Job chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer completed after 154.98s with status: succeeded
Stopping job with name chaiml-ir-v4-dpo-irv13-89808-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.53s
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-v4-dpo-irv13-89808-v1
Waiting for inference service chaiml-ir-v4-dpo-irv13-89808-v1 to be ready
Failed to get response for submission chaiml-cai-v1-1-dpo-ins_70786_v2: HTTPConnectionPool(host='chaiml-cai-v1-1-dpo-ins-70786-v2-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-ir-v4-dpo-irv13-89808-v1 ready after 110.65222954750061s
Pipeline stage MKMLDeployer completed in 111.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9563512802124023s
Received healthy response to inference request in 2.5542964935302734s
Received healthy response to inference request in 2.263486385345459s
Received healthy response to inference request in 2.4298739433288574s
Received healthy response to inference request in 2.333505153656006s
5 requests
0 failed requests
5th percentile: 2.2774901390075684
10th percentile: 2.2914938926696777
20th percentile: 2.3195013999938965
30th percentile: 2.352778911590576
40th percentile: 2.391326427459717
50th percentile: 2.4298739433288574
60th percentile: 2.479642963409424
70th percentile: 2.5294119834899904
80th percentile: 2.634707450866699
90th percentile: 2.795529365539551
95th percentile: 2.8759403228759766
99th percentile: 2.9402690887451173
mean time: 2.5075026512145997
Pipeline stage StressChecker completed in 14.08s
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 1.00s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv13-_89808_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 3118.42s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv13-_89808_v1 status is now inactive due to auto deactivation removed underperforming models