developer_uid: rirv938
submission_id: chaiml-ssnew-v5-dpo-lr_24415_v10
model_name: chaiml-ssnew-v5-dpo-lr_24415_v10
model_group: ChaiML/ssnew-v5-dpo-lr5e
status: torndown
timestamp: 2025-12-12T18:28:35+00:00
num_battles: 6492
num_wins: 3217
celo_rating: 1295.21
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/ssnew-v5-dpo-lr5e6b01-lora
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': 0.3772899325164217, 'latency_mean': 2.650364079475403, 'latency_p50': 2.6522369384765625, 'latency_p90': 2.8929603099823}, {'batch_size': 2, 'throughput': 0.5659719795559532, 'latency_mean': 3.527058058977127, 'latency_p50': 3.517017126083374, 'latency_p90': 3.8180659294128416}, {'batch_size': 3, 'throughput': 0.6953899646810277, 'latency_mean': 4.294590986967087, 'latency_p50': 4.287185907363892, 'latency_p90': 4.9064733505249025}, {'batch_size': 4, 'throughput': 0.7907617666305753, 'latency_mean': 5.0316556930542, 'latency_p50': 5.018068313598633, 'latency_p90': 5.868534898757934}, {'batch_size': 5, 'throughput': 0.8479932960252896, 'latency_mean': 5.874632788896561, 'latency_p50': 5.862500548362732, 'latency_p90': 6.664043140411377}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-ssnew-v5-dpo-lr_24415_v10
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/ssnew-v5-dpo-lr5e6b01-lora
model_size: 24B
ranking_group: single
throughput_3p7s: 0.6
us_pacific_date: 2025-11-26
win_ratio: 0.4955329636475662
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '####', '</s>', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{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-ssnew-v5-dpo-lr-24415-v10-mkmlizer
Waiting for job on chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer to finish
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║                                                                     ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║                                                                     ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║                                                                     ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║                                                                     ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ║                                                                     ║
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: Downloaded to shared memory in 47.317s
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: Checking if ChaiML/ssnew-v5-dpo-lr5e6b01-lora already exists in ChaiML
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvp0aj933, device:0
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: quantized model in 58.167s
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: Processed model ChaiML/ssnew-v5-dpo-lr5e6b01-lora in 105.485s
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia/config.json
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia/tokenizer_config.json
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia/special_tokens_map.json
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia/tokenizer.json
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v5-dpo-lr-24415-v10/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:19, 18.63it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:42,  8.48it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:20, 17.14it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:24, 14.03it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:27, 12.56it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:20, 17.08it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 15.03it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.40it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.37it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:15, 20.52it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:14, 21.76it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:16, 19.26it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:12, 26.08it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 23.96it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.69it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:10, 27.84it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:10, 29.15it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:11, 25.33it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:13, 21.38it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 27.25it/s]
Loading 0:  23%|██▎       | 83/363 [00:03<00:10, 27.89it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:11, 24.32it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:10, 26.95it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:10, 26.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:04<00:08, 29.37it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 27.49it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.88it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.94it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:10, 23.14it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:08, 28.93it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:08, 26.83it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 29.84it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.76it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:07, 28.07it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:06, 34.37it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:10, 20.59it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 22.94it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:08, 24.54it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:09, 21.62it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 26.12it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 23.49it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.56it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 21.59it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 23.07it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 23.62it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:06, 23.62it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:03,  1.50s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:21,  1.26s/it]
Loading 0:  57%|█████▋    | 208/363 [00:28<02:00,  1.28it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<01:30,  1.68it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<01:06,  2.22it/s]
Loading 0:  60%|██████    | 218/363 [00:28<00:44,  3.23it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:33,  4.18it/s]
Loading 0:  62%|██████▏   | 224/363 [00:29<00:27,  5.13it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:17,  7.76it/s]
Loading 0:  64%|██████▍   | 232/363 [00:29<00:13,  9.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:09, 13.23it/s]
Loading 0:  66%|██████▋   | 241/363 [00:29<00:07, 15.30it/s]
Loading 0:  68%|██████▊   | 246/363 [00:29<00:05, 19.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:05, 21.00it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:04, 25.25it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:04, 24.96it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:03, 31.63it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:04, 21.57it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:03, 24.53it/s]
Loading 0:  77%|███████▋  | 278/363 [00:30<00:03, 26.16it/s]
Loading 0:  78%|███████▊  | 282/363 [00:30<00:02, 28.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:31<00:02, 27.39it/s]
Loading 0:  80%|████████  | 291/363 [00:31<00:02, 30.99it/s]
Loading 0:  81%|████████▏ | 295/363 [00:31<00:02, 28.50it/s]
Loading 0:  82%|████████▏ | 299/363 [00:31<00:02, 29.34it/s]
Loading 0:  84%|████████▎ | 304/363 [00:31<00:02, 24.82it/s]
Loading 0:  85%|████████▍ | 307/363 [00:31<00:02, 23.41it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:02, 24.61it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 24.75it/s]
Loading 0:  88%|████████▊ | 318/363 [00:32<00:01, 28.60it/s]
Loading 0:  88%|████████▊ | 321/363 [00:32<00:01, 25.27it/s]
Loading 0:  90%|█████████ | 327/363 [00:32<00:01, 30.33it/s]
Loading 0:  91%|█████████ | 331/363 [00:32<00:01, 28.40it/s]
Loading 0:  92%|█████████▏| 335/363 [00:32<00:00, 29.57it/s]
Loading 0:  93%|█████████▎| 339/363 [00:33<00:00, 29.52it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:01, 17.79it/s]
Loading 0:  96%|█████████▌| 348/363 [00:33<00:00, 19.39it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:00, 25.99it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00, 25.02it/s]
                                                            

Job chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer completed after 256.19s with status: succeeded
Stopping job with name chaiml-ssnew-v5-dpo-lr-24415-v10-mkmlizer
Pipeline stage MKMLizer completed in 256.80s
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-ssnew-v5-dpo-lr-24415-v10
Waiting for inference service chaiml-ssnew-v5-dpo-lr-24415-v10 to be ready
Inference service chaiml-ssnew-v5-dpo-lr-24415-v10 ready after 162.329656124115s
Pipeline stage MKMLDeployer completed in 163.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5828752517700195s
Received healthy response to inference request in 2.119736909866333s
Received healthy response to inference request in 2.3751702308654785s
Received healthy response to inference request in 2.1616172790527344s
Received healthy response to inference request in 2.099605083465576s
5 requests
0 failed requests
5th percentile: 2.1036314487457277
10th percentile: 2.107657814025879
20th percentile: 2.1157105445861815
30th percentile: 2.1281129837036135
40th percentile: 2.144865131378174
50th percentile: 2.1616172790527344
60th percentile: 2.247038459777832
70th percentile: 2.33245964050293
80th percentile: 2.4167112350463866
90th percentile: 2.4997932434082033
95th percentile: 2.5413342475891114
99th percentile: 2.574567050933838
mean time: 2.2678009510040282
Pipeline stage StressChecker completed in 12.59s
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 0.79s
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-ssnew-v5-dpo-lr_24415_v10 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 0.12s
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-ssnew-v5-dpo-lr-24415-v10-profiler
Waiting for inference service chaiml-ssnew-v5-dpo-lr-24415-v10-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5089.07s
Shutdown handler de-registered
chaiml-ssnew-v5-dpo-lr_24415_v10 status is now torndown due to DeploymentManager action