chaiml-gy-exp139-dpo-ex_14494

developer_uid: bogoconic1

submission_id: chaiml-gy-exp139-dpo-ex_14494_v1

model_name: chaiml-gy-exp139-dpo-ex_14494_v1

model_group: ChaiML/gy-exp139-dpo-exp

status: torndown

timestamp: 2025-07-10T18:00:35+00:00

num_battles: 8786

num_wins: 4553

celo_rating: 1301.13

family_friendly_score: 0.5786

family_friendly_standard_error: 0.006983151723971061

submission_type: basic

model_repo: ChaiML/gy-exp139-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifflt0-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': 0.5250306640779424, 'latency_mean': 1.9045545446872711, 'latency_p50': 1.8957806825637817, 'latency_p90': 2.1121905565261843}, {'batch_size': 3, 'throughput': 1.0550042808714168, 'latency_mean': 2.834228253364563, 'latency_p50': 2.833752751350403, 'latency_p90': 3.1095977306365965}, {'batch_size': 5, 'throughput': 1.3582629534498685, 'latency_mean': 3.664323614835739, 'latency_p50': 3.6527897119522095, 'latency_p90': 4.091987371444702}, {'batch_size': 6, 'throughput': 1.4450495331658637, 'latency_mean': 4.113025684356689, 'latency_p50': 4.144843578338623, 'latency_p90': 4.580483436584473}, {'batch_size': 8, 'throughput': 1.5926622823036827, 'latency_mean': 4.98280035853386, 'latency_p50': 5.045602440834045, 'latency_p90': 5.616980838775635}, {'batch_size': 10, 'throughput': 1.6774205801672066, 'latency_mean': 5.903135659694672, 'latency_p50': 5.887492418289185, 'latency_p90': 6.660163497924804}]

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

display_name: chaiml-gy-exp139-dpo-ex_14494_v1

is_internal_developer: False

language_model: ChaiML/gy-exp139-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifflt0-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-07-10

win_ratio: 0.5182107898930116

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-exp139-dpo-ex-14494-v1-mkmlizer
Waiting for job on chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer to finish
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: Downloaded to shared memory in 156.568s
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: Checking if ChaiML/gy-exp139-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifflt0-ep2 already exists in ChaiML
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmdmjwapo, device:0
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: quantized model in 55.617s
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: Processed model ChaiML/gy-exp139-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifflt0-ep2 in 212.186s
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia/config.json
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia/special_tokens_map.json
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia/tokenizer_config.json
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia/tokenizer.json
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp139-dpo-ex-14494-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.71it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.18it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.79it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.66it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.67it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.10it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:09, 34.53it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:15, 21.48it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:15, 21.32it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:18, 17.65it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:14, 22.32it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 23.34it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 22.45it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 23.79it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 24.29it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 24.98it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 26.90it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 19.69it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 19.99it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:12, 21.96it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:14, 19.42it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:12, 21.52it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:14, 18.51it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:12, 21.80it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:12, 21.43it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:12, 21.94it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 22.66it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 21.75it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:11, 22.57it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:14, 17.55it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:12, 19.57it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:12, 20.04it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 21.49it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 23.04it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.71it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 24.43it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:09, 24.35it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 23.65it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:09, 24.98it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:08, 25.15it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 23.30it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 24.76it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 28.21it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:11, 18.64it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:10, 19.43it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:12, 16.54it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:08, 22.50it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 23.30it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 23.04it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.21it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 23.80it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:08, 22.86it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 24.00it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 26.08it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.64it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.90it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 20.35it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 21.85it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 21.85it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<04:42,  1.75s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<03:39,  1.37s/it]
Loading 0:  57%|█████▋    | 208/363 [00:25<01:59,  1.30it/s]
Loading 0:  58%|█████▊    | 211/363 [00:26<01:27,  1.73it/s]
Loading 0:  59%|█████▉    | 214/363 [00:26<01:03,  2.35it/s]
Loading 0:  60%|██████    | 218/363 [00:26<00:42,  3.44it/s]
Loading 0:  61%|██████    | 221/363 [00:26<00:31,  4.46it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:25,  5.38it/s]
Loading 0:  63%|██████▎   | 228/363 [00:26<00:17,  7.64it/s]
Loading 0:  64%|██████▎   | 231/363 [00:27<00:14,  9.00it/s]
Loading 0:  65%|██████▌   | 237/363 [00:27<00:09, 13.45it/s]
Loading 0:  66%|██████▌   | 240/363 [00:27<00:08, 14.24it/s]
Loading 0:  68%|██████▊   | 246/363 [00:27<00:06, 19.03it/s]
Loading 0:  69%|██████▊   | 249/363 [00:27<00:06, 18.53it/s]
Loading 0:  70%|██████▉   | 253/363 [00:27<00:05, 21.98it/s]
Loading 0:  71%|███████   | 256/363 [00:27<00:04, 23.00it/s]
Loading 0:  71%|███████▏  | 259/363 [00:28<00:04, 22.43it/s]
Loading 0:  72%|███████▏  | 263/363 [00:28<00:03, 26.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:28<00:03, 26.97it/s]
Loading 0:  74%|███████▍  | 269/363 [00:28<00:05, 18.45it/s]
Loading 0:  75%|███████▍  | 272/363 [00:28<00:04, 19.45it/s]
Loading 0:  76%|███████▌  | 275/363 [00:28<00:05, 16.37it/s]
Loading 0:  77%|███████▋  | 280/363 [00:29<00:03, 22.27it/s]
Loading 0:  78%|███████▊  | 283/363 [00:29<00:03, 22.82it/s]
Loading 0:  79%|███████▉  | 286/363 [00:29<00:03, 22.08it/s]
Loading 0:  80%|████████  | 291/363 [00:29<00:02, 25.32it/s]
Loading 0:  81%|████████  | 294/363 [00:29<00:03, 22.45it/s]
Loading 0:  82%|████████▏ | 298/363 [00:29<00:02, 26.06it/s]
Loading 0:  83%|████████▎ | 303/363 [00:29<00:02, 28.32it/s]
Loading 0:  85%|████████▍ | 307/363 [00:30<00:03, 18.60it/s]
Loading 0:  85%|████████▌ | 310/363 [00:30<00:02, 19.71it/s]
Loading 0:  86%|████████▌ | 313/363 [00:30<00:02, 20.18it/s]
Loading 0:  87%|████████▋ | 316/363 [00:30<00:02, 21.76it/s]
Loading 0:  88%|████████▊ | 319/363 [00:30<00:01, 22.53it/s]
Loading 0:  89%|████████▊ | 322/363 [00:30<00:01, 22.15it/s]
Loading 0:  90%|█████████ | 327/363 [00:31<00:01, 25.47it/s]
Loading 0:  91%|█████████ | 330/363 [00:31<00:01, 22.72it/s]
Loading 0:  92%|█████████▏| 334/363 [00:31<00:01, 26.46it/s]
Loading 0:  93%|█████████▎| 337/363 [00:31<00:01, 22.14it/s]
Loading 0:  94%|█████████▍| 341/363 [00:32<00:01, 14.20it/s]
Loading 0:  95%|█████████▌| 346/363 [00:32<00:00, 19.23it/s]
Loading 0:  96%|█████████▌| 349/363 [00:32<00:00, 17.96it/s]
Loading 0:  97%|█████████▋| 353/363 [00:32<00:00, 21.14it/s]
Loading 0:  98%|█████████▊| 356/363 [00:32<00:00, 22.52it/s]
Loading 0:  99%|█████████▉| 359/363 [00:32<00:00, 22.44it/s]
                                                            
Job chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer completed after 249.66s with status: succeeded
Stopping job with name chaiml-gy-exp139-dpo-ex-14494-v1-mkmlizer
Pipeline stage MKMLizer completed in 250.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp139-dpo-ex-14494-v1
Waiting for inference service chaiml-gy-exp139-dpo-ex-14494-v1 to be ready
Failed to get response for submission blend_fader_2025-07-10: HTTPConnectionPool(host='chaiml-exp-grpo-cp312-9-36146-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x759ad872f450>, 'Connection to chaiml-exp-grpo-cp312-9-36146-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-gy-exp139-dpo-ex-14494-v1 ready after 200.760559797287s
Pipeline stage MKMLDeployer completed in 201.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7243614196777344s
Received healthy response to inference request in 2.135847330093384s
Received healthy response to inference request in 2.068772315979004s
Received healthy response to inference request in 1.8320679664611816s
Received healthy response to inference request in 2.0348949432373047s
5 requests
0 failed requests
5th percentile: 1.8726333618164062
10th percentile: 1.913198757171631
20th percentile: 1.9943295478820802
30th percentile: 2.0416704177856446
40th percentile: 2.055221366882324
50th percentile: 2.068772315979004
60th percentile: 2.0956023216247557
70th percentile: 2.122432327270508
80th percentile: 2.253550148010254
90th percentile: 2.488955783843994
95th percentile: 2.606658601760864
99th percentile: 2.7008208560943605
mean time: 2.1591887950897215
Pipeline stage StressChecker completed in 12.28s
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 0.70s
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 0.80s
Shutdown handler de-registered
chaiml-gy-exp139-dpo-ex_14494_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 3203.61s
Shutdown handler de-registered
chaiml-gy-exp139-dpo-ex_14494_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp139-dpo-ex_14494_v1 status is now torndown due to DeploymentManager action