developer_uid: bogoconic1
submission_id: chaiml-gy-exp6-sftdpo-g_23103_v1
model_name: chaiml-gy-exp6-sftdpo-g_23103_v1
model_group: ChaiML/gy-exp6-sftdpo-gy
status: torndown
timestamp: 2025-06-25T13:57:06+00:00
num_battles: 9344
num_wins: 3827
celo_rating: 1222.4
family_friendly_score: 0.7654
family_friendly_standard_error: 0.005992709570803511
submission_type: basic
model_repo: ChaiML/gy-exp6-sftdpo-gy-1301-3905-pref-grok-onlylast-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': 0.5958744669276806, 'latency_mean': 1.6780984997749329, 'latency_p50': 1.6817861795425415, 'latency_p90': 1.8505491971969605}, {'batch_size': 3, 'throughput': 1.0570834925144357, 'latency_mean': 2.82621333360672, 'latency_p50': 2.8289941549301147, 'latency_p90': 3.0849654197692873}, {'batch_size': 5, 'throughput': 1.2717152783231493, 'latency_mean': 3.9198252320289613, 'latency_p50': 3.9148595333099365, 'latency_p90': 4.344274878501892}, {'batch_size': 6, 'throughput': 1.334062245529929, 'latency_mean': 4.466347805261612, 'latency_p50': 4.500522255897522, 'latency_p90': 5.019232606887817}, {'batch_size': 8, 'throughput': 1.400709823878983, 'latency_mean': 5.675147588253021, 'latency_p50': 5.700758337974548, 'latency_p90': 6.298799014091491}, {'batch_size': 10, 'throughput': 1.435307066480514, 'latency_mean': 6.907348803281784, 'latency_p50': 6.897492289543152, 'latency_p90': 7.747218632698059}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp6-sftdpo-g_23103_v1
is_internal_developer: True
language_model: ChaiML/gy-exp6-sftdpo-gy-1301-3905-pref-grok-onlylast-ep2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-06-25
win_ratio: 0.4095676369863014
generation_params: {'temperature': 0.45, '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': 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-exp6-sftdpo-g-23103-v1-mkmlizer
Waiting for job on chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer to finish
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ belonging to: ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ║ ║
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: Downloaded to shared memory in 42.055s
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: Checking if ChaiML/gy-exp6-sftdpo-gy-1301-3905-pref-grok-onlylast-ep2 already exists in ChaiML
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5_g8qk84, device:0
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: quantized model in 32.048s
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: Processed model ChaiML/gy-exp6-sftdpo-gy-1301-3905-pref-grok-onlylast-ep2 in 74.104s
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp6-sftdpo-g-23103-v1
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp6-sftdpo-g-23103-v1/config.json
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp6-sftdpo-g-23103-v1/special_tokens_map.json
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp6-sftdpo-g-23103-v1/tokenizer_config.json
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp6-sftdpo-g-23103-v1/tokenizer.json
chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.08it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 47.45it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 48.38it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 39.15it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:07, 44.03it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:07, 43.36it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 44.06it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:06, 45.47it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:08, 37.60it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:06, 45.42it/s] Loading 0: 17%|█▋ | 62/363 [00:01<00:09, 30.60it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:09, 31.67it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:13, 22.03it/s] Loading 0: 20%|██ | 74/363 [00:02<00:12, 23.41it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:09, 29.02it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:09, 29.79it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:08, 33.76it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 34.18it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 38.57it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:06, 40.92it/s] Loading 0: 30%|███ | 109/363 [00:03<00:06, 41.97it/s] Loading 0: 31%|███▏ | 114/363 [00:03<00:06, 36.27it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 34.38it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 42.45it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 42.51it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 42.10it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 42.02it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 25.65it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 26.17it/s] Loading 0: 42%|████▏ | 154/363 [00:04<00:06, 30.69it/s] Loading 0: 44%|████▎ | 158/363 [00:04<00:06, 30.03it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 37.25it/s] Loading 0: 47%|████▋ | 170/363 [00:04<00:05, 37.76it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 38.62it/s] Loading 0: 50%|████▉ | 180/363 [00:05<00:04, 40.11it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:05, 32.16it/s] Loading 0: 52%|█████▏ | 190/363 [00:05<00:04, 35.82it/s] Loading 0: 53%|█████▎ | 194/363 [00:05<00:05, 32.97it/s] Loading 0: 55%|█████▍ | 199/363 [00:05<00:04, 36.85it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:04, 35.97it/s] Loading 0: 57%|█████▋ | 208/363 [00:05<00:04, 36.21it/s] Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 32.00it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:03, 36.39it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 26.76it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.15it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 27.68it/s] Loading 0: 65%|██████▍ | 235/363 [00:06<00:04, 29.95it/s] Loading 0: 66%|██████▌ | 239/363 [00:06<00:04, 28.99it/s] Loading 0: 67%|██████▋ | 244/363 [00:07<00:03, 33.67it/s] Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 31.58it/s] Loading 0: 70%|██████▉ | 253/363 [00:07<00:03, 35.94it/s] Loading 0: 71%|███████ | 257/363 [00:07<00:03, 32.87it/s] Loading 0: 72%|███████▏ | 262/363 [00:07<00:02, 37.04it/s] Loading 0: 73%|███████▎ | 266/363 [00:07<00:02, 32.53it/s] Loading 0: 75%|███████▍ | 271/363 [00:07<00:02, 36.73it/s] Loading 0: 76%|███████▌ | 275/363 [00:07<00:02, 33.57it/s] Loading 0: 77%|███████▋ | 280/363 [00:08<00:02, 36.88it/s] Loading 0: 78%|███████▊ | 284/363 [00:08<00:02, 33.38it/s] Loading 0: 80%|███████▉ | 289/363 [00:08<00:01, 37.20it/s] Loading 0: 81%|████████ | 293/363 [00:08<00:02, 33.36it/s] Loading 0: 82%|████████▏ | 298/363 [00:08<00:01, 37.39it/s] Loading 0: 83%|████████▎ | 303/363 [00:08<00:01, 38.85it/s] Loading 0: 85%|████████▍ | 308/363 [00:09<00:02, 19.84it/s] Loading 0: 86%|████████▌ | 312/363 [00:09<00:02, 20.79it/s] Loading 0: 88%|████████▊ | 319/363 [00:09<00:01, 28.17it/s] Loading 0: 89%|████████▉ | 323/363 [00:09<00:01, 29.10it/s] Loading 0: 90%|█████████ | 328/363 [00:09<00:01, 32.64it/s] Loading 0: 91%|█████████▏| 332/363 [00:09<00:00, 32.50it/s] Loading 0: 93%|█████████▎| 337/363 [00:10<00:00, 35.62it/s] Loading 0: 94%|█████████▍| 341/363 [00:10<00:00, 34.71it/s] Loading 0: 95%|█████████▌| 346/363 [00:10<00:00, 37.28it/s] Loading 0: 96%|█████████▋| 350/363 [00:10<00:00, 35.83it/s] Loading 0: 98%|█████████▊| 355/363 [00:10<00:00, 37.57it/s] Loading 0: 99%|█████████▉| 359/363 [00:10<00:00, 36.02it/s]
Job chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer completed after 104.21s with status: succeeded
Stopping job with name chaiml-gy-exp6-sftdpo-g-23103-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp6-sftdpo-g-23103-v1
Waiting for inference service chaiml-gy-exp6-sftdpo-g-23103-v1 to be ready
Inference service chaiml-gy-exp6-sftdpo-g-23103-v1 ready after 150.6538589000702s
Pipeline stage MKMLDeployer completed in 151.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1377766132354736s
Received healthy response to inference request in 1.9593474864959717s
Received healthy response to inference request in 2.0887861251831055s
Received healthy response to inference request in 1.577845811843872s
Received healthy response to inference request in 1.677474021911621s
5 requests
0 failed requests
5th percentile: 1.597771453857422
10th percentile: 1.6176970958709718
20th percentile: 1.6575483798980712
30th percentile: 1.7338487148284911
40th percentile: 1.8465981006622314
50th percentile: 1.9593474864959717
60th percentile: 2.011122941970825
70th percentile: 2.0628983974456787
80th percentile: 2.098584222793579
90th percentile: 2.1181804180145263
95th percentile: 2.127978515625
99th percentile: 2.135816993713379
mean time: 1.8882460117340087
Pipeline stage StressChecker completed in 10.80s
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 0.67s
Shutdown handler de-registered
chaiml-gy-exp6-sftdpo-g_23103_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
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 5357.43s
Shutdown handler de-registered
chaiml-gy-exp6-sftdpo-g_23103_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp6-sftdpo-g_23103_v1 status is now torndown due to DeploymentManager action