developer_uid: bogoconic1
submission_id: chaiml-gy-exp122-dpo-ex_18452_v3
model_name: chaiml-gy-exp122-dpo-ex_18452_v3
model_group: ChaiML/gy-exp122-dpo-exp
status: torndown
timestamp: 2025-07-08T15:20:52+00:00
num_battles: 10691
num_wins: 5769
celo_rating: 1323.98
family_friendly_score: 0.5025999999999999
family_friendly_standard_error: 0.007070972210382389
submission_type: basic
model_repo: ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-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': 0.5216489314335047, 'latency_mean': 1.916893297433853, 'latency_p50': 1.9390095472335815, 'latency_p90': 2.1394184112548826}, {'batch_size': 3, 'throughput': 1.0548190958117591, 'latency_mean': 2.833892501592636, 'latency_p50': 2.852561116218567, 'latency_p90': 3.152402091026306}, {'batch_size': 5, 'throughput': 1.349389564272848, 'latency_mean': 3.686817947626114, 'latency_p50': 3.676489472389221, 'latency_p90': 4.091877889633179}, {'batch_size': 6, 'throughput': 1.4464313365279204, 'latency_mean': 4.11644210100174, 'latency_p50': 4.129071116447449, 'latency_p90': 4.6310781955719}, {'batch_size': 8, 'throughput': 1.5836345250626425, 'latency_mean': 5.001186401844024, 'latency_p50': 4.990322828292847, 'latency_p90': 5.582312846183777}, {'batch_size': 10, 'throughput': 1.6786030915558812, 'latency_mean': 5.902084262371063, 'latency_p50': 5.907305359840393, 'latency_p90': 6.685157680511475}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp122-dpo-ex_18452_v3
is_internal_developer: False
language_model: ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2025-07-08
win_ratio: 0.5396127583949116
generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, '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-exp122-dpo-ex-18452-v3-mkmlizer
Waiting for job on chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer to finish
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ Version: 0.29.15 ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ belonging to: ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ║ ║
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: Downloaded to shared memory in 102.750s
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: Checking if ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnbjehl8h, device:0
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: quantized model in 53.623s
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: Processed model ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 156.374s
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia/config.json
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia/special_tokens_map.json
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia/tokenizer_config.json
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia/tokenizer.json
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v3/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 38.94it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:12, 28.58it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:11, 29.45it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:13, 25.96it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:11, 28.97it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:13, 24.77it/s] Loading 0: 8%|▊ | 30/363 [00:01<00:10, 32.62it/s] Loading 0: 9%|▉ | 34/363 [00:01<00:15, 21.39it/s] Loading 0: 10%|█ | 37/363 [00:01<00:16, 19.94it/s] Loading 0: 11%|█ | 40/363 [00:01<00:15, 21.34it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:14, 21.84it/s] Loading 0: 13%|█▎ | 47/363 [00:01<00:12, 25.77it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:15, 19.94it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:11, 25.78it/s] Loading 0: 16%|█▋ | 59/363 [00:02<00:13, 22.50it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:10, 27.84it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:09, 29.47it/s] Loading 0: 20%|██ | 73/363 [00:03<00:15, 18.46it/s] Loading 0: 22%|██▏ | 79/363 [00:03<00:12, 23.08it/s] Loading 0: 23%|██▎ | 83/363 [00:03<00:11, 23.92it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 23.49it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:11, 23.47it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:13, 19.40it/s] Loading 0: 27%|██▋ | 97/363 [00:04<00:10, 24.53it/s] Loading 0: 28%|██▊ | 100/363 [00:04<00:10, 25.15it/s] Loading 0: 28%|██▊ | 103/363 [00:04<00:10, 24.48it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:13, 19.50it/s] Loading 0: 31%|███ | 111/363 [00:04<00:11, 22.67it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:12, 20.70it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:10, 24.38it/s] Loading 0: 33%|███▎ | 121/363 [00:05<00:09, 24.54it/s] Loading 0: 34%|███▍ | 124/363 [00:05<00:10, 23.22it/s] Loading 0: 36%|███▌ | 129/363 [00:05<00:09, 25.87it/s] Loading 0: 36%|███▋ | 132/363 [00:05<00:10, 22.52it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:08, 26.11it/s] Loading 0: 38%|███▊ | 139/363 [00:05<00:08, 25.85it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 24.76it/s] Loading 0: 40%|███▉ | 145/363 [00:06<00:08, 25.85it/s] Loading 0: 41%|████ | 149/363 [00:06<00:07, 29.29it/s] Loading 0: 42%|████▏ | 153/363 [00:06<00:13, 15.28it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:11, 18.38it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:10, 19.21it/s] Loading 0: 45%|████▍ | 163/363 [00:07<00:09, 21.01it/s] Loading 0: 46%|████▌ | 166/363 [00:07<00:09, 21.76it/s] Loading 0: 47%|████▋ | 169/363 [00:07<00:09, 21.51it/s] Loading 0: 48%|████▊ | 174/363 [00:07<00:07, 24.36it/s] Loading 0: 49%|████▉ | 177/363 [00:07<00:08, 21.46it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:07, 25.24it/s] Loading 0: 51%|█████ | 186/363 [00:07<00:06, 26.91it/s] Loading 0: 52%|█████▏ | 189/363 [00:08<00:11, 15.18it/s] Loading 0: 53%|█████▎ | 193/363 [00:08<00:09, 18.18it/s] Loading 0: 54%|█████▍ | 196/363 [00:08<00:09, 17.11it/s] Loading 0: 55%|█████▌ | 200/363 [00:19<00:09, 17.11it/s] Loading 0: 55%|█████▌ | 201/363 [00:24<03:18, 1.23s/it] Loading 0: 56%|█████▌ | 203/363 [00:24<02:45, 1.03s/it] Loading 0: 57%|█████▋ | 208/363 [00:24<01:40, 1.55it/s] Loading 0: 58%|█████▊ | 211/363 [00:25<01:16, 1.99it/s] Loading 0: 59%|█████▊ | 213/363 [00:25<01:03, 2.37it/s] Loading 0: 60%|█████▉ | 217/363 [00:25<00:41, 3.55it/s] Loading 0: 61%|██████ | 220/363 [00:25<00:32, 4.42it/s] Loading 0: 61%|██████▏ | 223/363 [00:25<00:24, 5.81it/s] Loading 0: 62%|██████▏ | 226/363 [00:26<00:21, 6.38it/s] Loading 0: 63%|██████▎ | 229/363 [00:26<00:16, 8.16it/s] Loading 0: 64%|██████▍ | 232/363 [00:26<00:13, 9.87it/s] Loading 0: 65%|██████▍ | 235/363 [00:26<00:10, 12.11it/s] Loading 0: 66%|██████▌ | 238/363 [00:26<00:08, 14.16it/s] Loading 0: 66%|██████▋ | 241/363 [00:26<00:07, 15.61it/s] Loading 0: 67%|██████▋ | 244/363 [00:26<00:06, 17.73it/s] Loading 0: 68%|██████▊ | 247/363 [00:27<00:05, 19.41it/s] Loading 0: 69%|██████▉ | 250/363 [00:27<00:05, 18.87it/s] Loading 0: 70%|██████▉ | 253/363 [00:27<00:05, 20.73it/s] Loading 0: 71%|███████ | 256/363 [00:27<00:04, 21.89it/s] Loading 0: 71%|███████▏ | 259/363 [00:27<00:04, 21.03it/s] Loading 0: 73%|███████▎ | 264/363 [00:27<00:03, 27.00it/s] Loading 0: 74%|███████▎ | 267/363 [00:28<00:05, 17.36it/s] Loading 0: 74%|███████▍ | 270/363 [00:28<00:06, 15.09it/s] Loading 0: 75%|███████▌ | 274/363 [00:28<00:04, 18.34it/s] Loading 0: 76%|███████▋ | 277/363 [00:28<00:04, 18.75it/s] Loading 0: 77%|███████▋ | 280/363 [00:28<00:04, 20.45it/s] Loading 0: 78%|███████▊ | 283/363 [00:28<00:03, 21.20it/s] Loading 0: 79%|███████▉ | 286/363 [00:29<00:03, 20.92it/s] Loading 0: 80%|███████▉ | 289/363 [00:29<00:03, 22.09it/s] Loading 0: 80%|████████ | 292/363 [00:29<00:03, 22.51it/s] Loading 0: 81%|████████▏ | 295/363 [00:29<00:03, 21.99it/s] Loading 0: 82%|████████▏ | 298/363 [00:29<00:02, 23.28it/s] Loading 0: 83%|████████▎ | 303/363 [00:29<00:02, 25.50it/s] Loading 0: 84%|████████▍ | 306/363 [00:30<00:03, 14.52it/s] Loading 0: 85%|████████▌ | 310/363 [00:30<00:02, 17.77it/s] Loading 0: 86%|████████▌ | 313/363 [00:30<00:02, 18.48it/s] Loading 0: 87%|████████▋ | 316/363 [00:30<00:02, 19.96it/s] Loading 0: 88%|████████▊ | 319/363 [00:30<00:02, 21.21it/s] Loading 0: 89%|████████▊ | 322/363 [00:30<00:02, 20.16it/s] Loading 0: 90%|████████▉ | 325/363 [00:30<00:01, 21.19it/s] Loading 0: 90%|█████████ | 328/363 [00:31<00:01, 21.84it/s] Loading 0: 91%|█████████ | 331/363 [00:31<00:01, 20.87it/s] Loading 0: 92%|█████████▏| 334/363 [00:31<00:01, 22.32it/s] Loading 0: 93%|█████████▎| 337/363 [00:31<00:01, 18.38it/s] Loading 0: 94%|█████████▎| 340/363 [00:31<00:01, 19.97it/s] Loading 0: 94%|█████████▍| 343/363 [00:32<00:01, 11.27it/s] Loading 0: 96%|█████████▌| 347/363 [00:32<00:01, 15.02it/s] Loading 0: 96%|█████████▋| 350/363 [00:32<00:00, 15.70it/s] Loading 0: 97%|█████████▋| 353/363 [00:32<00:00, 17.47it/s] Loading 0: 98%|█████████▊| 356/363 [00:32<00:00, 19.13it/s] Loading 0: 99%|█████████▉| 359/363 [00:32<00:00, 19.64it/s] Loading 0: 100%|█████████▉| 362/363 [00:32<00:00, 21.25it/s]
Job chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer completed after 188.94s with status: succeeded
Stopping job with name chaiml-gy-exp122-dpo-ex-18452-v3-mkmlizer
Pipeline stage MKMLizer completed in 189.46s
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-exp122-dpo-ex-18452-v3
Waiting for inference service chaiml-gy-exp122-dpo-ex-18452-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-gy-exp122-dpo-ex-18452-v3 ready after 191.60698866844177s
Pipeline stage MKMLDeployer completed in 192.40s
run pipeline stage %s
Running pipeline stage StressChecker
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 2.7166011333465576s
Received healthy response to inference request in 5.745128631591797s
Received healthy response to inference request in 2.04679799079895s
Received healthy response to inference request in 4.855980396270752s
Received healthy response to inference request in 1.964949607849121s
5 requests
0 failed requests
5th percentile: 1.981319284439087
10th percentile: 1.9976889610290527
20th percentile: 2.0304283142089843
30th percentile: 2.1807586193084716
40th percentile: 2.448679876327515
50th percentile: 2.7166011333465576
60th percentile: 3.572352838516235
70th percentile: 4.4281045436859126
80th percentile: 5.033810043334961
90th percentile: 5.389469337463379
95th percentile: 5.5672989845275875
99th percentile: 5.709562702178955
mean time: 3.4658915519714357
%s, retrying in %s seconds...
Received healthy response to inference request in 3.9052670001983643s
Received healthy response to inference request in 2.1211955547332764s
Received healthy response to inference request in 7.120912313461304s
Received healthy response to inference request in 1.8855435848236084s
Received healthy response to inference request in 3.512962818145752s
5 requests
0 failed requests
5th percentile: 1.932673978805542
10th percentile: 1.9798043727874757
20th percentile: 2.074065160751343
30th percentile: 2.3995490074157715
40th percentile: 2.9562559127807617
50th percentile: 3.512962818145752
60th percentile: 3.6698844909667967
70th percentile: 3.826806163787842
80th percentile: 4.548396062850953
90th percentile: 5.8346541881561285
95th percentile: 6.477783250808715
99th percentile: 6.992286500930786
mean time: 3.709176254272461
%s, retrying in %s seconds...
Received healthy response to inference request in 2.15317702293396s
Received healthy response to inference request in 1.905226230621338s
Received healthy response to inference request in 1.8342585563659668s
Received healthy response to inference request in 15.872811317443848s
Received healthy response to inference request in 2.051299810409546s
5 requests
0 failed requests
5th percentile: 1.848452091217041
10th percentile: 1.8626456260681152
20th percentile: 1.8910326957702637
30th percentile: 1.9344409465789796
40th percentile: 1.9928703784942627
50th percentile: 2.051299810409546
60th percentile: 2.0920506954193114
70th percentile: 2.132801580429077
80th percentile: 4.89710388183594
90th percentile: 10.384957599639893
95th percentile: 13.128884458541869
99th percentile: 15.324025945663452
mean time: 4.7633545875549315
Pipeline stage StressChecker completed in 64.14s
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 0.72s
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 0.74s
Shutdown handler de-registered
chaiml-gy-exp122-dpo-ex_18452_v3 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp122-dpo-ex-18452-v3-profiler
Waiting for inference service chaiml-gy-exp122-dpo-ex-18452-v3-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3423.48s
Shutdown handler de-registered
chaiml-gy-exp122-dpo-ex_18452_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp122-dpo-ex_18452_v3 status is now torndown due to DeploymentManager action