chaiml-ir-v4-dpo-irv13-_88629

developer_uid: chai_backend_admin

submission_id: chaiml-ir-v4-dpo-irv13-_88629_v1

model_name: training123

model_group: ChaiML/ir-v4-dpo_irv13-l

status: inactive

timestamp: 2025-10-29T16:47:48+00:00

num_battles: 6261

num_wins: 3085

celo_rating: 1294.98

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ir-v4-dpo_irv13-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': 0.37542832621689015, 'latency_mean': 2.6635266184806823, 'latency_p50': 2.669516086578369, 'latency_p90': 2.8902195930480956}, {'batch_size': 2, 'throughput': 0.5615279150491744, 'latency_mean': 3.549328796863556, 'latency_p50': 3.5634987354278564, 'latency_p90': 3.847857427597046}, {'batch_size': 3, 'throughput': 0.6849096476637273, 'latency_mean': 4.3618218457698825, 'latency_p50': 4.390289545059204, 'latency_p90': 4.752874231338501}, {'batch_size': 4, 'throughput': 0.7774354415137954, 'latency_mean': 5.131708530187606, 'latency_p50': 5.118934392929077, 'latency_p90': 5.782234454154968}, {'batch_size': 5, 'throughput': 0.8370697052103673, 'latency_mean': 5.949103169441223, 'latency_p50': 5.935750722885132, 'latency_p90': 6.724731516838074}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ir-v4-dpo_irv13-lr5e6b01-cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.59

us_pacific_date: 2025-10-29

win_ratio: 0.4927327902890912

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', 'You:', 'User:', '</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-dpo-irv13-88629-v1-mkmlizer
Waiting for job on chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer to finish
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ║                                                                     ║
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: Downloaded to shared memory in 61.720s
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: Checking if ChaiML/ir-v4-dpo_irv13-lr5e6b01-cosine already exists in ChaiML
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9gdjqf0k, device:0
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: quantized model in 42.166s
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: Processed model ChaiML/ir-v4-dpo_irv13-lr5e6b01-cosine in 103.886s
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia/config.json
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia/special_tokens_map.json
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-dpo-irv13-88629-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia/tokenizer_config.json
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia/tokenizer.json
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-dpo-irv13-88629-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.37it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.42it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.70it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.08it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.17it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.72it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.78it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.84it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.74it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:12, 23.62it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:16, 18.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.24it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.09it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:15, 19.35it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:14, 20.08it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:13, 21.00it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:13, 20.48it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.98it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:10, 26.76it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:10, 25.53it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.98it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 29.53it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 26.54it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.59it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.71it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.86it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 31.74it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.30it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:06, 33.40it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 36.67it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 34.26it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 40.87it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 25.96it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.16it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.97it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.88it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.45it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 33.05it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.47it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.69it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.43it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:54,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.72it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:28,  4.97it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.91it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.53it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:10, 11.88it/s]
Loading 0:  66%|██████▌   | 238/363 [00:21<00:08, 15.20it/s]
Loading 0:  67%|██████▋   | 242/363 [00:21<00:06, 18.23it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.52it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.20it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.43it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.81it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 26.37it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.11it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.27it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.53it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.67it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.88it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.91it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.24it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.63it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.94it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.94it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 32.19it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 35.73it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 34.01it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 34.61it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 35.15it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.75it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.45it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 30.10it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.47it/s]
                                                            
Job chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer completed after 194.77s with status: succeeded
Stopping job with name chaiml-ir-v4-dpo-irv13-88629-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.36s
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-irv13-88629-v1
Waiting for inference service chaiml-ir-v4-dpo-irv13-88629-v1 to be ready
Inference service chaiml-ir-v4-dpo-irv13-88629-v1 ready after 110.68373966217041s
Pipeline stage MKMLDeployer completed in 112.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5052530765533447s
Received healthy response to inference request in 2.2931315898895264s
Received healthy response to inference request in 2.1770482063293457s
Received healthy response to inference request in 2.362602949142456s
Received healthy response to inference request in 2.4236531257629395s
5 requests
0 failed requests
5th percentile: 2.200264883041382
10th percentile: 2.223481559753418
20th percentile: 2.26991491317749
30th percentile: 2.3070258617401125
40th percentile: 2.3348144054412843
50th percentile: 2.362602949142456
60th percentile: 2.3870230197906492
70th percentile: 2.411443090438843
80th percentile: 2.4399731159210205
90th percentile: 2.4726130962371826
95th percentile: 2.4889330863952637
99th percentile: 2.5019890785217287
mean time: 2.3523377895355226
Pipeline stage StressChecker completed in 13.20s
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 0.67s
Shutdown handler de-registered
chaiml-ir-v4-dpo-irv13-_88629_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 5775.83s
Shutdown handler de-registered