chaiml-gy-exp162-lipo-g_88566

developer_uid: bogoconic1

submission_id: chaiml-gy-exp162-lipo-g_88566_v1

model_name: chaiml-gy-exp162-lipo-g_88566_v1

model_group: ChaiML/gy-exp162-lipo-gy

status: torndown

timestamp: 2025-07-14T06:40:20+00:00

num_battles: 6554

num_wins: 3577

celo_rating: 1328.66

family_friendly_score: 0.5142

family_friendly_standard_error: 0.0070682156164056

submission_type: basic

model_repo: ChaiML/gy-exp162-lipo-gy-datamix-v3-bo12-dpo-gt0.6-3ans-ep3

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': 0.5231107471102895, 'latency_mean': 1.9115338456630706, 'latency_p50': 1.9247957468032837, 'latency_p90': 2.113214898109436}, {'batch_size': 3, 'throughput': 1.069419969718766, 'latency_mean': 2.7899401140213014, 'latency_p50': 2.7737518548965454, 'latency_p90': 3.100351905822754}, {'batch_size': 5, 'throughput': 1.376941729782687, 'latency_mean': 3.6056764936447143, 'latency_p50': 3.603714346885681, 'latency_p90': 4.044376516342163}, {'batch_size': 6, 'throughput': 1.4851541119012257, 'latency_mean': 4.013103823661805, 'latency_p50': 4.002143621444702, 'latency_p90': 4.5209452390670775}, {'batch_size': 8, 'throughput': 1.6186546546703464, 'latency_mean': 4.892808586359024, 'latency_p50': 4.936384201049805, 'latency_p90': 5.498251104354859}, {'batch_size': 10, 'throughput': 1.7255759805795852, 'latency_mean': 5.738502403497696, 'latency_p50': 5.763531684875488, 'latency_p90': 6.470787429809571}]

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

display_name: chaiml-gy-exp162-lipo-g_88566_v1

is_internal_developer: False

language_model: ChaiML/gy-exp162-lipo-gy-datamix-v3-bo12-dpo-gt0.6-3ans-ep3

model_size: 24B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2025-07-13

win_ratio: 0.545773573390296

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': ['\n', '<|im_end|>', '<|im_start|>'], '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-exp162-lipo-g-88566-v1-mkmlizer
Waiting for job on chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer to finish
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: Downloaded to shared memory in 82.965s
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: Checking if ChaiML/gy-exp162-lipo-gy-datamix-v3-bo12-dpo-gt0.6-3ans-ep3 already exists in ChaiML
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8h18jo1l, device:0
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: quantized model in 60.564s
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: Processed model ChaiML/gy-exp162-lipo-gy-datamix-v3-bo12-dpo-gt0.6-3ans-ep3 in 143.531s
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia/config.json
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia/special_tokens_map.json
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia/tokenizer_config.json
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia/tokenizer.json
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp162-lipo-g-88566-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:12, 29.35it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:16, 21.30it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:15, 22.99it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:14, 24.02it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:16, 21.54it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:15, 22.31it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:15, 22.42it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:15, 21.24it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:14, 22.45it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 25.09it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:21, 15.12it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:20, 15.79it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:20, 15.77it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:20, 15.38it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 19.32it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:15, 20.56it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:15, 20.53it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:14, 21.77it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:13, 22.44it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:14, 21.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:13, 22.90it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:11, 25.74it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:16, 17.38it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:15, 18.02it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:14, 20.03it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:14, 19.22it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.86it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:12, 22.48it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.40it/s]
Loading 0:  27%|██▋       | 99/363 [00:04<00:10, 26.07it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 22.93it/s]
Loading 0:  29%|██▉       | 106/363 [00:05<00:09, 25.77it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:13, 19.51it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:11, 21.32it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:11, 21.22it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 22.72it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:09, 24.33it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.58it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:09, 23.73it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:09, 25.22it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:09, 23.70it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 23.80it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 24.59it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 23.64it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 24.62it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 27.05it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:12, 17.56it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 18.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:13, 15.47it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 20.93it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 22.09it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 21.81it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 22.64it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 23.18it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 22.36it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:07, 23.35it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:07, 24.94it/s]
Loading 0:  52%|█████▏    | 189/363 [00:09<00:12, 14.43it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:09, 17.50it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:09, 18.15it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:08, 19.48it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:08, 19.48it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<05:13,  1.94s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<04:03,  1.52s/it]
Loading 0:  57%|█████▋    | 208/363 [00:28<02:12,  1.17it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<01:37,  1.57it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:18,  1.92it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:49,  2.96it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:37,  3.83it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:27,  5.10it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:22,  6.02it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:17,  7.76it/s]
Loading 0:  64%|██████▍   | 232/363 [00:29<00:13,  9.52it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:10, 11.74it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:08, 14.00it/s]
Loading 0:  66%|██████▋   | 241/363 [00:30<00:07, 15.37it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:06, 17.84it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:05, 19.88it/s]
Loading 0:  69%|██████▉   | 250/363 [00:30<00:05, 19.76it/s]
Loading 0:  70%|██████▉   | 253/363 [00:30<00:05, 21.39it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:04, 23.03it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:04, 21.47it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:04, 22.66it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:03, 25.79it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:05, 16.94it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 18.09it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:05, 15.84it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:03, 21.93it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:03, 23.24it/s]
Loading 0:  79%|███████▉  | 286/363 [00:32<00:03, 22.96it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:02, 25.93it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:03, 22.76it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:02, 25.99it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:02, 27.37it/s]
Loading 0:  84%|████████▍ | 306/363 [00:33<00:03, 17.04it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:02, 19.64it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 19.74it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 21.17it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:02, 21.79it/s]
Loading 0:  89%|████████▊ | 322/363 [00:33<00:01, 21.12it/s]
Loading 0:  90%|████████▉ | 325/363 [00:33<00:01, 22.47it/s]
Loading 0:  90%|█████████ | 328/363 [00:34<00:01, 23.28it/s]
Loading 0:  91%|█████████ | 331/363 [00:34<00:01, 21.97it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 23.79it/s]
Loading 0:  93%|█████████▎| 337/363 [00:34<00:01, 19.95it/s]
Loading 0:  94%|█████████▎| 340/363 [00:34<00:01, 22.14it/s]
Loading 0:  94%|█████████▍| 343/363 [00:35<00:01, 12.34it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:00, 16.12it/s]
Loading 0:  96%|█████████▋| 350/363 [00:35<00:00, 17.20it/s]
Loading 0:  97%|█████████▋| 353/363 [00:35<00:00, 19.55it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.40it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 20.96it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 22.64it/s]
                                                            
Job chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer completed after 187.01s with status: succeeded
Stopping job with name chaiml-gy-exp162-lipo-g-88566-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.47s
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-exp162-lipo-g-88566-v1
Waiting for inference service chaiml-gy-exp162-lipo-g-88566-v1 to be ready
Failed to get response for submission junhua024-chai-1-full-066126_v17: HTTPConnectionPool(host='junhua024-chai-1-full-066126-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-gy-exp162-lipo-g-88566-v1 ready after 221.41149139404297s
Pipeline stage MKMLDeployer completed in 221.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.50671648979187s
Received healthy response to inference request in 2.077815294265747s
Received healthy response to inference request in 2.0177648067474365s
Received healthy response to inference request in 1.8675687313079834s
Received healthy response to inference request in 2.065248489379883s
5 requests
0 failed requests
5th percentile: 1.897607946395874
10th percentile: 1.9276471614837647
20th percentile: 1.987725591659546
30th percentile: 2.0272615432739256
40th percentile: 2.046255016326904
50th percentile: 2.065248489379883
60th percentile: 2.0702752113342284
70th percentile: 2.075301933288574
80th percentile: 2.1635955333709718
90th percentile: 2.3351560115814207
95th percentile: 2.4209362506866454
99th percentile: 2.4895604419708253
mean time: 2.107022762298584
Pipeline stage StressChecker completed in 11.86s
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 0.75s
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 0.62s
Shutdown handler de-registered
chaiml-gy-exp162-lipo-g_88566_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 3062.17s
Shutdown handler de-registered
chaiml-gy-exp162-lipo-g_88566_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp162-lipo-g_88566_v1 status is now torndown due to DeploymentManager action