chaiml-gy-exp68-sft-gy-_49852

developer_uid: bogoconic1

submission_id: chaiml-gy-exp68-sft-gy-_49852_v1

model_name: chaiml-gy-exp68-sft-gy-_49852_v1

model_group: ChaiML/gy-exp68-sft-gy-d

status: torndown

timestamp: 2025-07-03T07:33:42+00:00

num_battles: 7964

num_wins: 3832

celo_rating: 1277.38

family_friendly_score: 0.5516

family_friendly_standard_error: 0.007033312732987209

submission_type: basic

model_repo: ChaiML/gy-exp68-sft-gy-datamix-v1-head1000-AR-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5946326576296511, 'latency_mean': 1.6816071677207947, 'latency_p50': 1.686654806137085, 'latency_p90': 1.8558216094970703}, {'batch_size': 3, 'throughput': 1.0517140030147225, 'latency_mean': 2.8463797295093536, 'latency_p50': 2.844769597053528, 'latency_p90': 3.086143088340759}, {'batch_size': 5, 'throughput': 1.2636163452702094, 'latency_mean': 3.9384345030784607, 'latency_p50': 3.9437708854675293, 'latency_p90': 4.411909008026123}, {'batch_size': 6, 'throughput': 1.3170086380492976, 'latency_mean': 4.517984949350357, 'latency_p50': 4.4937580823898315, 'latency_p90': 5.074096012115478}, {'batch_size': 8, 'throughput': 1.3714832212465218, 'latency_mean': 5.787888731956482, 'latency_p50': 5.794283390045166, 'latency_p90': 6.568952870368958}, {'batch_size': 10, 'throughput': 1.4143949963208753, 'latency_mean': 7.0116140437126155, 'latency_p50': 7.060120224952698, 'latency_p90': 7.873453545570373}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp68-sft-gy-_49852_v1

is_internal_developer: True

language_model: ChaiML/gy-exp68-sft-gy-datamix-v1-head1000-AR-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-07-03

win_ratio: 0.48116524359618285

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_end|>', '<|im_start|>', '\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-exp68-sft-gy-49852-v1-mkmlizer
Waiting for job on chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer to finish
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: Downloaded to shared memory in 39.674s
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: Checking if ChaiML/gy-exp68-sft-gy-datamix-v1-head1000-AR-ep2 already exists in ChaiML
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjjdxl3g1, device:0
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: quantized model in 31.105s
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: Processed model ChaiML/gy-exp68-sft-gy-datamix-v1-head1000-AR-ep2 in 70.779s
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp68-sft-gy-49852-v1/nvidia
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp68-sft-gy-49852-v1/nvidia/config.json
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp68-sft-gy-49852-v1/nvidia/special_tokens_map.json
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp68-sft-gy-49852-v1/nvidia/tokenizer_config.json
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp68-sft-gy-49852-v1/nvidia/tokenizer.json
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp68-sft-gy-49852-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.11it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.10it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.69it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.60it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.49it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.81it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.06it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.53it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.63it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.94it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.15it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 40.40it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.21it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 40.69it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 39.95it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 39.98it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 41.20it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 43.10it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 36.01it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:07, 33.41it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.21it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.51it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.31it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 41.87it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.69it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.40it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.04it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.99it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 34.97it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.11it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 38.29it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 38.78it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 39.52it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:04, 40.80it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:04, 34.08it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 41.59it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.40it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 41.00it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 40.90it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 42.01it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 25.23it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 26.20it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.00it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 35.68it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.42it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 37.74it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 36.71it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 41.30it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 42.26it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 42.30it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.51it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.61it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 39.35it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 39.07it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 43.60it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 21.23it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 23.38it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 30.78it/s]
Loading 0:  89%|████████▉ | 324/363 [00:08<00:01, 32.78it/s]
Loading 0:  91%|█████████ | 329/363 [00:08<00:00, 35.68it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 38.49it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 33.72it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 41.91it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 42.88it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 37.73it/s]
                                                            
Job chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer completed after 96.03s with status: succeeded
Stopping job with name chaiml-gy-exp68-sft-gy-49852-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp68-sft-gy-49852-v1
Waiting for inference service chaiml-gy-exp68-sft-gy-49852-v1 to be ready
Inference service chaiml-gy-exp68-sft-gy-49852-v1 ready after 343.0060842037201s
Pipeline stage MKMLDeployer completed in 343.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.243304967880249s
Received healthy response to inference request in 2.187260866165161s
Received healthy response to inference request in 1.9029083251953125s
Received healthy response to inference request in 2.189962863922119s
Received healthy response to inference request in 1.7197182178497314s
5 requests
0 failed requests
5th percentile: 1.7563562393188477
10th percentile: 1.7929942607879639
20th percentile: 1.8662703037261963
30th percentile: 1.9597788333892823
40th percentile: 2.0735198497772216
50th percentile: 2.187260866165161
60th percentile: 2.188341665267944
70th percentile: 2.1894224643707276
80th percentile: 2.200631284713745
90th percentile: 2.2219681262969972
95th percentile: 2.232636547088623
99th percentile: 2.2411712837219238
mean time: 2.0486310482025147
Pipeline stage StressChecker completed in 11.51s
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 0.96s
Shutdown handler de-registered
chaiml-gy-exp68-sft-gy-_49852_v1 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-exp68-sft-gy-49852-v1-profiler
Waiting for inference service chaiml-gy-exp68-sft-gy-49852-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5063.71s
Shutdown handler de-registered
chaiml-gy-exp68-sft-gy-_49852_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp68-sft-gy-_49852_v1 status is now torndown due to DeploymentManager action