chaiml-gy-exp187-sft-gy_32706

developer_uid: bogoconic1

submission_id: chaiml-gy-exp187-sft-gy_32706_v3

model_name: chaiml-gy-exp187-sft-gy_32706_v3

model_group: ChaiML/gy-exp187-sft-gy-

status: torndown

timestamp: 2025-07-19T21:32:47+00:00

num_battles: 7318

num_wins: 3180

celo_rating: 1237.9

family_friendly_score: 0.7618

family_friendly_standard_error: 0.0060242968054371295

submission_type: basic

model_repo: ChaiML/gy-exp187-sft-gy-datamix-v1-bo8-reward-gt0.7-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': 0.5257795030335574, 'latency_mean': 1.9018199682235717, 'latency_p50': 1.8951232433319092, 'latency_p90': 2.1062671899795533}, {'batch_size': 3, 'throughput': 1.0621629467730505, 'latency_mean': 2.8134055745601656, 'latency_p50': 2.8127758502960205, 'latency_p90': 3.1340853214263915}, {'batch_size': 5, 'throughput': 1.338794089499929, 'latency_mean': 3.7119162452220915, 'latency_p50': 3.7140003442764282, 'latency_p90': 4.148204374313354}, {'batch_size': 6, 'throughput': 1.4377962198514438, 'latency_mean': 4.129387286901474, 'latency_p50': 4.138352632522583, 'latency_p90': 4.6242855310440065}, {'batch_size': 8, 'throughput': 1.5905851224007992, 'latency_mean': 4.97691158413887, 'latency_p50': 4.962282180786133, 'latency_p90': 5.594138431549072}, {'batch_size': 10, 'throughput': 1.6662304185909615, 'latency_mean': 5.942187846899032, 'latency_p50': 5.982062816619873, 'latency_p90': 6.688887214660644}]

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

display_name: chaiml-gy-exp187-sft-gy_32706_v3

is_internal_developer: False

language_model: ChaiML/gy-exp187-sft-gy-datamix-v1-bo8-reward-gt0.7-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-19

win_ratio: 0.4345449576386991

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_start|>', '</s>', '<|im_end|>', '\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-exp187-sft-gy-32706-v3-mkmlizer
Waiting for job on chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer to finish
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: Downloaded to shared memory in 66.914s
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: Checking if ChaiML/gy-exp187-sft-gy-datamix-v1-bo8-reward-gt0.7-ep2 already exists in ChaiML
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw0uu7ehg, device:0
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: quantized model in 47.439s
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: Processed model ChaiML/gy-exp187-sft-gy-datamix-v1-bo8-reward-gt0.7-ep2 in 114.353s
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia/special_tokens_map.json
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia/config.json
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia/tokenizer_config.json
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia/tokenizer.json
Failed to get response for submission junhua024-chai-16-full-12_429_v2: HTTPConnectionPool(host='junhua024-chai-16-full-12-429-v2-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 0x7b772c626f90>, 'Connection to junhua024-chai-16-full-12-429-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp187-sft-gy-32706-v3/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.46it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.48it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.61it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.64it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.54it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.74it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.50it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.19it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.32it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.81it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 28.83it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.72it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.15it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.91it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.54it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:12, 22.83it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.10it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.58it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.62it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.50it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.53it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.85it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.69it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.54it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.76it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.12it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.65it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:08, 25.68it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.76it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.75it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.97it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.04it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 21.73it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.07it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.62it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.17it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.06it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.05it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.99it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.51it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.27it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.75it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.83it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.24it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.24it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.91it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.15it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.30it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.30it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.33it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.91it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.80it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.13it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.90it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.11it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.05it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.45it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 22.81it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.36it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.66it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.06it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.58it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.41it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.00it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.11it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.39it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.25it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.38it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.36it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.55it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 26.53it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 23.59it/s]
Loading 0:  90%|████████▉ | 326/363 [00:26<00:01, 29.28it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.28it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.49it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.22it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.99it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 21.65it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.43it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.74it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 24.04it/s]
                                                            
Job chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer completed after 148.42s with status: succeeded
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-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 0x7b760c5778d0>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Stopping job with name chaiml-gy-exp187-sft-gy-32706-v3-mkmlizer
Pipeline stage MKMLizer completed in 149.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp187-sft-gy-32706-v3
Waiting for inference service chaiml-gy-exp187-sft-gy-32706-v3 to be ready
Failed to get response for submission junhua024-chai-16-full-12_429_v2: HTTPConnectionPool(host='junhua024-chai-16-full-12-429-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-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 0x7b766c2bba90>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-gy-exp187-sft-gy-32706-v3 ready after 331.5192561149597s
Pipeline stage MKMLDeployer completed in 332.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3412439823150635s
Received healthy response to inference request in 1.9564452171325684s
Received healthy response to inference request in 1.729750633239746s
Received healthy response to inference request in 1.9093613624572754s
Received healthy response to inference request in 2.1732771396636963s
5 requests
0 failed requests
5th percentile: 1.765672779083252
10th percentile: 1.8015949249267578
20th percentile: 1.8734392166137694
30th percentile: 1.918778133392334
40th percentile: 1.9376116752624513
50th percentile: 1.9564452171325684
60th percentile: 2.0431779861450194
70th percentile: 2.1299107551574705
80th percentile: 2.20687050819397
90th percentile: 2.2740572452545167
95th percentile: 2.30765061378479
99th percentile: 2.3345253086090088
mean time: 2.02201566696167
Pipeline stage StressChecker completed in 11.66s
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 0.74s
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 0.77s
Shutdown handler de-registered
chaiml-gy-exp187-sft-gy_32706_v3 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
%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 6309.96s
Shutdown handler de-registered
chaiml-gy-exp187-sft-gy_32706_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp187-sft-gy_32706_v3 status is now torndown due to DeploymentManager action