chaiml-gy-exp12-sft-gy-_52107

developer_uid: bogoconic1

submission_id: chaiml-gy-exp12-sft-gy-_52107_v1

model_name: chaiml-gy-exp12-sft-gy-_52107_v1

model_group: ChaiML/gy-exp12-sft-gy-1

status: torndown

timestamp: 2025-06-26T09:40:01+00:00

num_battles: 8138

num_wins: 4179

celo_rating: 1298.83

family_friendly_score: 0.5256000000000001

family_friendly_standard_error: 0.007061793539887725

submission_type: basic

model_repo: ChaiML/gy-exp12-sft-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5958038151063357, 'latency_mean': 1.6782737255096436, 'latency_p50': 1.6814565658569336, 'latency_p90': 1.8557987928390502}, {'batch_size': 3, 'throughput': 1.0798997920478477, 'latency_mean': 2.7687836682796476, 'latency_p50': 2.7886691093444824, 'latency_p90': 3.0416991472244264}, {'batch_size': 5, 'throughput': 1.3019534409408844, 'latency_mean': 3.825435463190079, 'latency_p50': 3.8029948472976685, 'latency_p90': 4.223901224136353}, {'batch_size': 6, 'throughput': 1.3480533106542534, 'latency_mean': 4.421537359952927, 'latency_p50': 4.429232478141785, 'latency_p90': 4.935591006278992}, {'batch_size': 8, 'throughput': 1.4292454126920044, 'latency_mean': 5.563526122570038, 'latency_p50': 5.530132532119751, 'latency_p90': 6.235230112075806}, {'batch_size': 10, 'throughput': 1.4525365620615256, 'latency_mean': 6.820072724819183, 'latency_p50': 6.789758563041687, 'latency_p90': 7.7207599401474}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp12-sft-gy-_52107_v1

is_internal_developer: False

language_model: ChaiML/gy-exp12-sft-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-06-26

win_ratio: 0.5135168346030966

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_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': 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-exp12-sft-gy-52107-v1-mkmlizer
Waiting for job on chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer to finish
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: Downloaded to shared memory in 39.463s
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: Checking if ChaiML/gy-exp12-sft-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz6ki4njr, device:0
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: quantized model in 30.996s
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: Processed model ChaiML/gy-exp12-sft-gy-1266-1301-7850-pref-grok-ctx2500-96tok-onlylast-ep2 in 70.459s
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gy-52107-v1
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gy-52107-v1/config.json
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gy-52107-v1/special_tokens_map.json
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gy-52107-v1/tokenizer_config.json
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gy-52107-v1/tokenizer.json
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gy-52107-v1/flywheel_model.0.safetensors
chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 29.93it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.51it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.23it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.76it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.28it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.09it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.17it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.69it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 47.36it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:07, 43.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.62it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.16it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 37.92it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 33.38it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 40.30it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.76it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 41.80it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 42.37it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 40.86it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 41.44it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 39.45it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.82it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.76it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.02it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 44.74it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.70it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 26.86it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.67it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.82it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.24it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.41it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.70it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.05it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.15it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 42.52it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:04, 41.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 33.22it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.43it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.89it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 41.40it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.13it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.54it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:04, 31.39it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:04, 29.47it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 37.03it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:03, 37.33it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 38.34it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 40.12it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 32.80it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 39.28it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 39.39it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:02, 39.91it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 40.47it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 33.78it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 38.51it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 21.88it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 23.84it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 23.96it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.04it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 34.86it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 35.88it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 40.67it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 41.36it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 42.77it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 43.73it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 36.11it/s]
                                                            
Job chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer completed after 94.77s with status: succeeded
Stopping job with name chaiml-gy-exp12-sft-gy-52107-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp12-sft-gy-52107-v1
Waiting for inference service chaiml-gy-exp12-sft-gy-52107-v1 to be ready
Inference service chaiml-gy-exp12-sft-gy-52107-v1 ready after 140.49341249465942s
Pipeline stage MKMLDeployer completed in 141.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.706813097000122s
Received healthy response to inference request in 1.6858062744140625s
Received healthy response to inference request in 1.7282254695892334s
Received healthy response to inference request in 2.014008045196533s
Received healthy response to inference request in 1.5374493598937988s
5 requests
0 failed requests
5th percentile: 1.5671207427978515
10th percentile: 1.5967921257019042
20th percentile: 1.6561348915100098
30th percentile: 1.6942901134490966
40th percentile: 1.7112577915191651
50th percentile: 1.7282254695892334
60th percentile: 1.8425384998321532
70th percentile: 1.9568515300750733
80th percentile: 2.152569055557251
90th percentile: 2.4296910762786865
95th percentile: 2.5682520866394043
99th percentile: 2.6791008949279784
mean time: 1.93446044921875
Pipeline stage StressChecker completed in 11.31s
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 0.76s
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 0.95s
Shutdown handler de-registered
chaiml-gy-exp12-sft-gy-_52107_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4951.23s
Shutdown handler de-registered
chaiml-gy-exp12-sft-gy-_52107_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp12-sft-gy-_52107_v1 status is now torndown due to DeploymentManager action