developer_uid: rirv938
submission_id: chaiml-gy-exp96-dpo-exp8_1696_v2
model_name: chaiml-gy-exp96-dpo-exp8_1696_v2
model_group: ChaiML/gy-exp96-dpo-exp8
status: torndown
timestamp: 2025-07-07T21:31:06+00:00
num_battles: 8356
num_wins: 4479
celo_rating: 1316.41
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/gy-exp96-dpo-exp86ep8s2-grok-payloads-0705-dpo-diff-gt0.05-ep1
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5171144563966789, 'latency_mean': 1.9336864304542543, 'latency_p50': 1.926257610321045, 'latency_p90': 2.1592835187911987}, {'batch_size': 3, 'throughput': 1.0387771707998157, 'latency_mean': 2.8768805932998656, 'latency_p50': 2.8612613677978516, 'latency_p90': 3.16687753200531}, {'batch_size': 5, 'throughput': 1.3246873565297461, 'latency_mean': 3.7565270125865937, 'latency_p50': 3.759406566619873, 'latency_p90': 4.1696666240692135}, {'batch_size': 6, 'throughput': 1.4297187631376143, 'latency_mean': 4.178236336708069, 'latency_p50': 4.185695767402649, 'latency_p90': 4.706744456291199}, {'batch_size': 8, 'throughput': 1.5553951298204487, 'latency_mean': 5.117364617586136, 'latency_p50': 5.075505971908569, 'latency_p90': 5.749815821647644}, {'batch_size': 10, 'throughput': 1.6353422071172712, 'latency_mean': 6.053277965784073, 'latency_p50': 6.063269853591919, 'latency_p90': 6.757525563240051}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp96-dpo-exp8_1696_v2
is_internal_developer: True
language_model: ChaiML/gy-exp96-dpo-exp86ep8s2-grok-payloads-0705-dpo-diff-gt0.05-ep1
model_size: 24B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-07-07
win_ratio: 0.5360220201053135
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', '###', 'You:', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp96-dpo-exp8-1696-v2-mkmlizer
Waiting for job on chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer to finish
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: Downloaded to shared memory in 53.183s
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: Checking if ChaiML/gy-exp96-dpo-exp86ep8s2-grok-payloads-0705-dpo-diff-gt0.05-ep1 already exists in ChaiML
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaf3duylr, device:0
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: quantized model in 53.968s
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: Processed model ChaiML/gy-exp96-dpo-exp86ep8s2-grok-payloads-0705-dpo-diff-gt0.05-ep1 in 107.152s
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia/config.json
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia/special_tokens_map.json
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia/tokenizer_config.json
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia/tokenizer.json
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp96-dpo-exp8-1696-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<01:12,  4.95it/s]
Loading 0:   1%|          | 4/363 [00:01<01:50,  3.26it/s]
Loading 0:   1%|▏         | 5/363 [00:01<01:59,  2.99it/s]
Loading 0:   3%|▎         | 10/363 [00:01<00:45,  7.84it/s]
Loading 0:   3%|▎         | 12/363 [00:01<00:46,  7.61it/s]
Loading 0:   4%|▍         | 14/363 [00:02<01:04,  5.43it/s]
Loading 0:   5%|▌         | 19/363 [00:02<00:36,  9.38it/s]
Loading 0:   6%|▌         | 21/363 [00:02<00:35,  9.69it/s]
Loading 0:   6%|▋         | 23/363 [00:03<00:34,  9.87it/s]
Loading 0:   8%|▊         | 28/363 [00:03<00:21, 15.38it/s]
Loading 0:   9%|▉         | 33/363 [00:03<00:19, 17.24it/s]
Loading 0:  10%|▉         | 36/363 [00:03<00:20, 16.11it/s]
Loading 0:  11%|█         | 40/363 [00:03<00:16, 19.34it/s]
Loading 0:  12%|█▏        | 43/363 [00:03<00:15, 20.44it/s]
Loading 0:  13%|█▎        | 48/363 [00:04<00:12, 24.43it/s]
Loading 0:  14%|█▍        | 51/363 [00:04<00:14, 22.15it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:11, 26.70it/s]
Loading 0:  17%|█▋        | 60/363 [00:04<00:12, 23.92it/s]
Loading 0:  18%|█▊        | 65/363 [00:04<00:11, 26.84it/s]
Loading 0:  19%|█▉        | 70/363 [00:05<00:12, 23.21it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:14, 19.68it/s]
Loading 0:  22%|██▏       | 79/363 [00:05<00:11, 25.15it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:11, 24.21it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:10, 26.39it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:10, 26.63it/s]
Loading 0:  25%|██▌       | 92/363 [00:06<00:13, 20.67it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:09, 27.91it/s]
Loading 0:  28%|██▊       | 103/363 [00:06<00:10, 26.00it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:12, 21.18it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:10, 24.31it/s]
Loading 0:  31%|███▏      | 114/363 [00:06<00:11, 21.98it/s]
Loading 0:  33%|███▎      | 120/363 [00:07<00:08, 27.09it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:09, 24.05it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:07, 29.42it/s]
Loading 0:  37%|███▋      | 133/363 [00:07<00:08, 27.04it/s]
Loading 0:  38%|███▊      | 138/363 [00:07<00:07, 29.55it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:08, 26.82it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:06, 33.28it/s]
Loading 0:  42%|████▏     | 152/363 [00:08<00:09, 23.02it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:08, 23.55it/s]
Loading 0:  44%|████▎     | 158/363 [00:08<00:10, 19.77it/s]
Loading 0:  45%|████▌     | 165/363 [00:08<00:07, 27.13it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:07, 25.95it/s]
Loading 0:  48%|████▊     | 174/363 [00:09<00:06, 28.34it/s]
Loading 0:  49%|████▉     | 178/363 [00:09<00:06, 26.71it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:06, 27.52it/s]
Loading 0:  52%|█████▏    | 187/363 [00:09<00:07, 24.54it/s]
Loading 0:  52%|█████▏    | 190/363 [00:09<00:07, 22.84it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:07, 23.81it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:06, 24.24it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:06, 24.24it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<03:14,  1.20s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<02:40,  1.00s/it]
Loading 0:  57%|█████▋    | 208/363 [00:25<01:36,  1.61it/s]
Loading 0:  58%|█████▊    | 211/363 [00:26<01:14,  2.05it/s]
Loading 0:  59%|█████▉    | 214/363 [00:26<00:55,  2.69it/s]
Loading 0:  60%|██████    | 218/363 [00:26<00:37,  3.87it/s]
Loading 0:  61%|██████    | 221/363 [00:26<00:28,  4.91it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:24,  5.78it/s]
Loading 0:  63%|██████▎   | 228/363 [00:26<00:16,  8.14it/s]
Loading 0:  64%|██████▎   | 231/363 [00:27<00:14,  9.27it/s]
Loading 0:  65%|██████▍   | 235/363 [00:27<00:10, 12.33it/s]
Loading 0:  66%|██████▌   | 238/363 [00:27<00:08, 14.52it/s]
Loading 0:  66%|██████▋   | 241/363 [00:27<00:07, 15.92it/s]
Loading 0:  67%|██████▋   | 245/363 [00:27<00:05, 20.07it/s]
Loading 0:  68%|██████▊   | 248/363 [00:27<00:06, 17.21it/s]
Loading 0:  70%|██████▉   | 253/363 [00:27<00:04, 22.59it/s]
Loading 0:  71%|███████   | 257/363 [00:28<00:05, 20.34it/s]
Loading 0:  72%|███████▏  | 262/363 [00:28<00:03, 25.28it/s]
Loading 0:  73%|███████▎  | 266/363 [00:28<00:03, 27.72it/s]
Loading 0:  74%|███████▍  | 270/363 [00:28<00:05, 17.03it/s]
Loading 0:  75%|███████▌  | 274/363 [00:28<00:04, 20.03it/s]
Loading 0:  76%|███████▋  | 277/363 [00:29<00:04, 20.08it/s]
Loading 0:  77%|███████▋  | 280/363 [00:29<00:03, 21.75it/s]
Loading 0:  78%|███████▊  | 283/363 [00:29<00:03, 22.85it/s]
Loading 0:  79%|███████▉  | 286/363 [00:29<00:03, 21.91it/s]
Loading 0:  80%|███████▉  | 289/363 [00:29<00:03, 23.20it/s]
Loading 0:  80%|████████  | 292/363 [00:29<00:03, 23.42it/s]
Loading 0:  81%|████████▏ | 295/363 [00:29<00:02, 23.53it/s]
Loading 0:  82%|████████▏ | 299/363 [00:29<00:02, 25.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:30<00:02, 22.14it/s]
Loading 0:  85%|████████▍ | 307/363 [00:30<00:02, 20.52it/s]
Loading 0:  85%|████████▌ | 310/363 [00:30<00:02, 21.45it/s]
Loading 0:  86%|████████▌ | 313/363 [00:30<00:02, 21.79it/s]
Loading 0:  88%|████████▊ | 318/363 [00:30<00:01, 26.44it/s]
Loading 0:  88%|████████▊ | 321/363 [00:30<00:01, 23.85it/s]
Loading 0:  90%|█████████ | 327/363 [00:31<00:01, 29.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:31<00:01, 27.80it/s]
Loading 0:  92%|█████████▏| 335/363 [00:31<00:00, 29.17it/s]
Loading 0:  93%|█████████▎| 339/363 [00:31<00:00, 28.57it/s]
Loading 0:  94%|█████████▍| 342/363 [00:31<00:01, 16.32it/s]
Loading 0:  96%|█████████▌| 347/363 [00:32<00:00, 20.19it/s]
Loading 0:  96%|█████████▋| 350/363 [00:32<00:00, 21.14it/s]
Loading 0:  98%|█████████▊| 355/363 [00:32<00:00, 25.61it/s]
Loading 0:  99%|█████████▉| 359/363 [00:32<00:00, 24.53it/s]
                                                            

Job chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer completed after 136.92s with status: succeeded
Stopping job with name chaiml-gy-exp96-dpo-exp8-1696-v2-mkmlizer
Pipeline stage MKMLizer completed in 137.43s
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-gy-exp96-dpo-exp8-1696-v2
Waiting for inference service chaiml-gy-exp96-dpo-exp8-1696-v2 to be ready
Inference service chaiml-gy-exp96-dpo-exp8-1696-v2 ready after 191.03194069862366s
Pipeline stage MKMLDeployer completed in 191.86s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.7814416885375977s
Received healthy response to inference request in 2.005176305770874s
Received healthy response to inference request in 2.114718198776245s
Received healthy response to inference request in 2.3768227100372314s
5 requests
1 failed requests
5th percentile: 2.0270846843719483
10th percentile: 2.0489930629730226
20th percentile: 2.092809820175171
30th percentile: 2.167139101028442
40th percentile: 2.271980905532837
50th percentile: 2.3768227100372314
60th percentile: 2.538670301437378
70th percentile: 2.7005178928375244
80th percentile: 6.25141410827637
90th percentile: 13.191358947753908
95th percentile: 16.66133136749267
99th percentile: 19.43730930328369
mean time: 5.881892538070678
%s, retrying in %s seconds...
Received healthy response to inference request in 2.134167194366455s
Received healthy response to inference request in 1.9646720886230469s
Received healthy response to inference request in 1.9330990314483643s
Received healthy response to inference request in 2.0854432582855225s
Received healthy response to inference request in 2.1514573097229004s
5 requests
0 failed requests
5th percentile: 1.9394136428833009
10th percentile: 1.9457282543182373
20th percentile: 1.9583574771881103
30th percentile: 1.988826322555542
40th percentile: 2.037134790420532
50th percentile: 2.0854432582855225
60th percentile: 2.1049328327178953
70th percentile: 2.1244224071502686
80th percentile: 2.137625217437744
90th percentile: 2.1445412635803223
95th percentile: 2.1479992866516113
99th percentile: 2.1507657051086424
mean time: 2.053767776489258
Pipeline stage StressChecker completed in 42.19s
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 0.67s
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 0.68s
Shutdown handler de-registered
chaiml-gy-exp96-dpo-exp8_1696_v2 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
Received signal 15, running shutdown handler
Shutdown handler de-registered
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...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Received signal 15, running shutdown handler
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 2984.39s
Shutdown handler de-registered
chaiml-gy-exp96-dpo-exp8_1696_v2 status is now torndown due to DeploymentManager action