chaiml-gy-exp20-sft-gy-_42297

developer_uid: bogoconic1

submission_id: chaiml-gy-exp20-sft-gy-_42297_v1

model_name: chaiml-gy-exp20-sft-gy-_42297_v1

model_group: ChaiML/gy-exp20-sft-gy-e

status: torndown

timestamp: 2025-06-26T21:35:01+00:00

num_battles: 8432

num_wins: 4260

celo_rating: 1293.77

family_friendly_score: 0.5282

family_friendly_standard_error: 0.007059812462098409

submission_type: basic

model_repo: ChaiML/gy-exp20-sft-gy-exp12sft-3696-pref-grok-ctx2500-96tok-onlylast-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5942742789763216, 'latency_mean': 1.6826246356964112, 'latency_p50': 1.6866512298583984, 'latency_p90': 1.8364112615585326}, {'batch_size': 3, 'throughput': 1.0856080824253498, 'latency_mean': 2.754751148223877, 'latency_p50': 2.7405730485916138, 'latency_p90': 3.0720234394073485}, {'batch_size': 5, 'throughput': 1.2850546988129, 'latency_mean': 3.877855633497238, 'latency_p50': 3.8684781789779663, 'latency_p90': 4.29802930355072}, {'batch_size': 6, 'throughput': 1.3586325703221376, 'latency_mean': 4.393976768255234, 'latency_p50': 4.377583742141724, 'latency_p90': 4.913162684440612}, {'batch_size': 8, 'throughput': 1.417323691409833, 'latency_mean': 5.613096381425858, 'latency_p50': 5.615487813949585, 'latency_p90': 6.297935342788696}, {'batch_size': 10, 'throughput': 1.4333166011842975, 'latency_mean': 6.923819043636322, 'latency_p50': 6.927691221237183, 'latency_p90': 7.755447506904602}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp20-sft-gy-_42297_v1

is_internal_developer: True

language_model: ChaiML/gy-exp20-sft-gy-exp12sft-3696-pref-grok-ctx2500-96tok-onlylast-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-06-26

win_ratio: 0.5052182163187856

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], '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': False}

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-exp20-sft-gy-42297-v1-mkmlizer
Waiting for job on chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer to finish
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: Downloaded to shared memory in 53.937s
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: Checking if ChaiML/gy-exp20-sft-gy-exp12sft-3696-pref-grok-ctx2500-96tok-onlylast-ep1 already exists in ChaiML
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9s86u5bm, device:0
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: quantized model in 30.300s
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: Processed model ChaiML/gy-exp20-sft-gy-exp12sft-3696-pref-grok-ctx2500-96tok-onlylast-ep1 in 84.238s
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp20-sft-gy-42297-v1
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp20-sft-gy-42297-v1/config.json
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp20-sft-gy-42297-v1/special_tokens_map.json
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp20-sft-gy-42297-v1/tokenizer_config.json
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp20-sft-gy-42297-v1/flywheel_model.0.safetensors
chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.12it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.05it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.78it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.91it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.03it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.55it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.89it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.93it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.18it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.05it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.32it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 38.51it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 39.83it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 41.01it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.71it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.59it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 43.16it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.78it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.90it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.29it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 38.70it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.99it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.99it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.16it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.04it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.92it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.35it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:06, 33.28it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.21it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.84it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.62it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.47it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.84it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.45it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.14it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.14it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.41it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.48it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.83it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.11it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.90it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.34it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.98it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.67it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.14it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.90it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.41it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 40.69it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.46it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.79it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 42.00it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.79it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.76it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.83it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.58it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 23.33it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.58it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 27.09it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 32.89it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 34.57it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 34.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 42.91it/s]
Loading 0:  94%|█████████▍| 343/363 [00:09<00:00, 43.73it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 37.24it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 45.20it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 42.38it/s]
                                                            
Job chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer completed after 104.51s with status: succeeded
Stopping job with name chaiml-gy-exp20-sft-gy-42297-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.04s
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-exp20-sft-gy-42297-v1
Waiting for inference service chaiml-gy-exp20-sft-gy-42297-v1 to be ready
Inference service chaiml-gy-exp20-sft-gy-42297-v1 ready after 150.5460844039917s
Pipeline stage MKMLDeployer completed in 151.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.213031768798828s
Received healthy response to inference request in 1.7658181190490723s
Received healthy response to inference request in 1.600487232208252s
{"detail":"HTTPConnectionPool(host='chaiml-gy-exp20-sft-gy-42297-v1-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 0x73f6ac430250>, 'Connection to chaiml-gy-exp20-sft-gy-42297-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 2.0169119834899902s
5 requests
1 failed requests
5th percentile: 1.633553409576416
10th percentile: 1.6666195869445801
20th percentile: 1.7327519416809083
30th percentile: 1.8160368919372558
40th percentile: 1.9164744377136231
50th percentile: 2.0169119834899902
60th percentile: 2.0953598976135255
70th percentile: 2.1738078117370607
80th percentile: 4.252020168304445
90th percentile: 8.329996967315676
95th percentile: 10.368985366821288
99th percentile: 12.00017608642578
mean time: 4.000844573974609
%s, retrying in %s seconds...
Received healthy response to inference request in 1.8646750450134277s
Received healthy response to inference request in 1.4482357501983643s
Received healthy response to inference request in 1.498255968093872s
Received healthy response to inference request in 1.6704175472259521s
Received healthy response to inference request in 1.5718169212341309s
5 requests
0 failed requests
5th percentile: 1.4582397937774658
10th percentile: 1.4682438373565674
20th percentile: 1.4882519245147705
30th percentile: 1.512968158721924
40th percentile: 1.5423925399780274
50th percentile: 1.5718169212341309
60th percentile: 1.6112571716308595
70th percentile: 1.6506974220275878
80th percentile: 1.7092690467834473
90th percentile: 1.7869720458984375
95th percentile: 1.8258235454559326
99th percentile: 1.8569047451019287
mean time: 1.6106802463531493
Pipeline stage StressChecker completed in 30.34s
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 0.70s
Shutdown handler de-registered
chaiml-gy-exp20-sft-gy-_42297_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 3097.20s
Shutdown handler de-registered
chaiml-gy-exp20-sft-gy-_42297_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp20-sft-gy-_42297_v1 status is now torndown due to DeploymentManager action