chaiml-gy-exp146-dpo-ex_52663

developer_uid: bogoconic1

submission_id: chaiml-gy-exp146-dpo-ex_52663_v4

model_name: chaiml-gy-exp146-dpo-ex_52663_v4

model_group: ChaiML/gy-exp146-dpo-exp

status: torndown

timestamp: 2025-07-13T07:02:22+00:00

num_battles: 10682

num_wins: 5699

celo_rating: 1321.17

family_friendly_score: 0.5374

family_friendly_standard_error: 0.007051258611056611

submission_type: basic

model_repo: ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2

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': 0.5190109715174257, 'latency_mean': 1.926618243455887, 'latency_p50': 1.9207597970962524, 'latency_p90': 2.135300850868225}, {'batch_size': 3, 'throughput': 1.0406721677331188, 'latency_mean': 2.8664372062683103, 'latency_p50': 2.8679099082946777, 'latency_p90': 3.2452873468399046}, {'batch_size': 5, 'throughput': 1.3192401040192292, 'latency_mean': 3.7710986125469206, 'latency_p50': 3.7724967002868652, 'latency_p90': 4.1833796262741085}, {'batch_size': 6, 'throughput': 1.4231649208324424, 'latency_mean': 4.1937979054450985, 'latency_p50': 4.168679475784302, 'latency_p90': 4.721947884559631}, {'batch_size': 8, 'throughput': 1.5492737603794788, 'latency_mean': 5.126818083524704, 'latency_p50': 5.169729232788086, 'latency_p90': 5.842919087409973}, {'batch_size': 10, 'throughput': 1.6263903776783282, 'latency_mean': 6.086206752061844, 'latency_p50': 6.088436007499695, 'latency_p90': 6.8498221158981325}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gy-exp146-dpo-ex_52663_v4

is_internal_developer: False

language_model: ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-07-13

win_ratio: 0.5335143231604569

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', '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-exp146-dpo-ex-52663-v4-mkmlizer
Waiting for job on chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer to finish
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: quantized model in 59.613s
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: Processed model ChaiML/gy-exp146-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.6-diffgt0.01-ep2 in 119.996s
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v4/nvidia
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v4/nvidia/config.json
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v4/nvidia/special_tokens_map.json
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v4/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp146-dpo-ex-52663-v4/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 31.69it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 25.84it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.34it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:16, 21.64it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:12, 28.41it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.00it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 31.03it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:16, 20.50it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:16, 19.25it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.44it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.63it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:13, 24.02it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.61it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 26.15it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 22.48it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.12it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.64it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 18.67it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:15, 19.19it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:13, 20.72it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 20.54it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.72it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 22.91it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.27it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.18it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 23.06it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:13, 18.91it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:11, 22.36it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 20.22it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 24.96it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.19it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 26.59it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.42it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.33it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:09, 23.51it/s]
Loading 0:  40%|████      | 146/363 [00:06<00:07, 28.64it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:10, 21.30it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 17.84it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 20.82it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:09, 20.96it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:08, 22.35it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 22.82it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.58it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.12it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 24.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 23.51it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 24.68it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 26.26it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 15.94it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.17it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 19.63it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 21.18it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 21.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<05:12,  1.93s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<04:02,  1.51s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<02:11,  1.18it/s]
Loading 0:  58%|█████▊    | 211/363 [00:27<01:36,  1.58it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:09,  2.13it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:50,  2.91it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:37,  3.80it/s]
Loading 0:  62%|██████▏   | 224/363 [00:28<00:27,  5.04it/s]
Loading 0:  63%|██████▎   | 228/363 [00:28<00:19,  7.08it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:15,  8.28it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:11, 11.25it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:09, 13.12it/s]
Loading 0:  66%|██████▋   | 241/363 [00:29<00:08, 14.62it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 16.98it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:06, 18.68it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:05, 19.13it/s]
Loading 0:  70%|██████▉   | 253/363 [00:29<00:05, 20.84it/s]
Loading 0:  71%|███████   | 256/363 [00:29<00:04, 21.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:04, 21.65it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:04, 22.56it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:03, 26.27it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:05, 16.32it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 17.58it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 14.64it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 19.63it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:03, 20.36it/s]
Loading 0:  79%|███████▉  | 286/363 [00:31<00:03, 20.42it/s]
Loading 0:  80%|███████▉  | 289/363 [00:31<00:03, 21.51it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:03, 22.21it/s]
Loading 0:  81%|████████▏ | 295/363 [00:31<00:03, 22.04it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:02, 23.30it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:02, 25.66it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 15.36it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:02, 18.35it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 19.11it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 20.46it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:02, 21.21it/s]
Loading 0:  89%|████████▊ | 322/363 [00:33<00:01, 21.75it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:01, 24.83it/s]
Loading 0:  91%|█████████ | 330/363 [00:33<00:01, 21.66it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 24.81it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 21.45it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 13.37it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 18.11it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 17.60it/s]
Loading 0:  97%|█████████▋| 353/363 [00:34<00:00, 20.94it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 22.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 21.85it/s]
                                                            
Job chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer completed after 155.47s with status: succeeded
Stopping job with name chaiml-gy-exp146-dpo-ex-52663-v4-mkmlizer
Pipeline stage MKMLizer completed in 156.14s
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-gy-exp146-dpo-ex-52663-v4
Waiting for inference service chaiml-gy-exp146-dpo-ex-52663-v4 to be ready
Inference service chaiml-gy-exp146-dpo-ex-52663-v4 ready after 220.87024903297424s
Pipeline stage MKMLDeployer completed in 221.33s
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 2.5596489906311035s
Received healthy response to inference request in 1.920649528503418s
Received healthy response to inference request in 1.8234283924102783s
Received healthy response to inference request in 1.940575361251831s
5 requests
1 failed requests
5th percentile: 1.8428726196289062
10th percentile: 1.8623168468475342
20th percentile: 1.90120530128479
30th percentile: 1.9246346950531006
40th percentile: 1.9326050281524658
50th percentile: 1.940575361251831
60th percentile: 2.18820481300354
70th percentile: 2.435834264755249
80th percentile: 6.076856899261477
90th percentile: 13.111272716522219
95th percentile: 16.628480625152584
99th percentile: 19.442246952056884
mean time: 5.677998161315918
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9835877418518066s
Received healthy response to inference request in 1.7722768783569336s
Received healthy response to inference request in 2.430117607116699s
Received healthy response to inference request in 1.9231674671173096s
Received healthy response to inference request in 1.8952839374542236s
5 requests
0 failed requests
5th percentile: 1.7968782901763916
10th percentile: 1.8214797019958495
20th percentile: 1.8706825256347657
30th percentile: 1.900860643386841
40th percentile: 1.9120140552520752
50th percentile: 1.9231674671173096
60th percentile: 1.9473355770111085
70th percentile: 1.9715036869049072
80th percentile: 2.0728937149047852
90th percentile: 2.251505661010742
95th percentile: 2.3408116340637206
99th percentile: 2.4122564125061037
mean time: 2.0008867263793944
Pipeline stage StressChecker completed in 41.48s
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 0.65s
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 0.79s
Shutdown handler de-registered
chaiml-gy-exp146-dpo-ex_52663_v4 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 0.10s
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-gy-exp146-dpo-ex-52663-v4-profiler
Waiting for inference service chaiml-gy-exp146-dpo-ex-52663-v4-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4684.38s
Shutdown handler de-registered
chaiml-gy-exp146-dpo-ex_52663_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp146-dpo-ex_52663_v4 status is now torndown due to DeploymentManager action