developer_uid: cycy233
submission_id: cycy233-model3-7_v1
model_name: 486
model_group: cycy233/model3-7
status: torndown
timestamp: 2025-02-28T09:15:58+00:00
num_battles: 7383
num_wins: 3636
celo_rating: 1250.53
family_friendly_score: 0.513
family_friendly_standard_error: 0.007068677386894949
submission_type: basic
model_repo: cycy233/model3-7
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.850996312930059, 'latency_mean': 1.1750263452529908, 'latency_p50': 1.1805598735809326, 'latency_p90': 1.3020890712738038}, {'batch_size': 4, 'throughput': 1.7778823914095507, 'latency_mean': 2.2436172378063204, 'latency_p50': 2.2556862831115723, 'latency_p90': 2.5055665254592894}, {'batch_size': 5, 'throughput': 1.9286683764156265, 'latency_mean': 2.5757775127887728, 'latency_p50': 2.5863534212112427, 'latency_p90': 2.8901708126068115}, {'batch_size': 8, 'throughput': 2.1088910046997458, 'latency_mean': 3.758744953870773, 'latency_p50': 3.7610483169555664, 'latency_p90': 4.2134624958038325}, {'batch_size': 10, 'throughput': 2.174951003302987, 'latency_mean': 4.555865746736527, 'latency_p50': 4.540789842605591, 'latency_p90': 5.112819218635559}, {'batch_size': 12, 'throughput': 2.207618747516543, 'latency_mean': 5.376213402748108, 'latency_p50': 5.394173979759216, 'latency_p90': 6.059180092811585}, {'batch_size': 15, 'throughput': 2.206077089379257, 'latency_mean': 6.714597380161285, 'latency_p50': 6.72760009765625, 'latency_p90': 7.40548357963562}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 486
is_internal_developer: False
language_model: cycy233/model3-7
model_size: 8B
ranking_group: single
throughput_3p7s: 2.12
us_pacific_date: 2025-02-28
win_ratio: 0.4924827305973182
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', '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 cycy233-model3-7-v1-mkmlizer
Waiting for job on cycy233-model3-7-v1-mkmlizer to finish
cycy233-model3-7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model3-7-v1-mkmlizer: ║ _____ __ __ ║
cycy233-model3-7-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-model3-7-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-model3-7-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-model3-7-v1-mkmlizer: ║ /___/ ║
cycy233-model3-7-v1-mkmlizer: ║ ║
cycy233-model3-7-v1-mkmlizer: ║ Version: 0.12.8 ║
cycy233-model3-7-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-model3-7-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-model3-7-v1-mkmlizer: ║ ║
cycy233-model3-7-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-model3-7-v1-mkmlizer: ║ belonging to: ║
cycy233-model3-7-v1-mkmlizer: ║ ║
cycy233-model3-7-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-model3-7-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-model3-7-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
cycy233-model3-7-v1-mkmlizer: ║ ║
cycy233-model3-7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
cycy233-model3-7-v1-mkmlizer: Downloaded to shared memory in 29.287s
cycy233-model3-7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3ma1rdxr, device:0
cycy233-model3-7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model3-7-v1-mkmlizer: quantized model in 28.151s
cycy233-model3-7-v1-mkmlizer: Processed model cycy233/model3-7 in 57.438s
cycy233-model3-7-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model3-7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model3-7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model3-7-v1
cycy233-model3-7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model3-7-v1/config.json
cycy233-model3-7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model3-7-v1/special_tokens_map.json
cycy233-model3-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model3-7-v1/tokenizer_config.json
cycy233-model3-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model3-7-v1/tokenizer.json
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
cycy233-model3-7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model3-7-v1/flywheel_model.0.safetensors
cycy233-model3-7-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 28.29it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 43.99it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 41.07it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 40.46it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 41.49it/s] Loading 0: 11%|█ | 32/291 [00:00<00:08, 31.85it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:07, 35.81it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:07, 32.75it/s] Loading 0: 16%|█▌ | 46/291 [00:01<00:06, 36.22it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:07, 34.05it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:05, 42.39it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:05, 42.64it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:05, 43.25it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 44.53it/s] Loading 0: 26%|██▋ | 77/291 [00:02<00:06, 34.78it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:07, 28.97it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 29.10it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 34.98it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:05, 34.39it/s] Loading 0: 35%|███▌ | 102/291 [00:02<00:05, 36.15it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 35.27it/s] Loading 0: 38%|███▊ | 111/291 [00:03<00:04, 38.52it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 38.39it/s] Loading 0: 41%|████ | 120/291 [00:03<00:04, 36.88it/s] Loading 0: 43%|████▎ | 124/291 [00:03<00:04, 35.48it/s] Loading 0: 44%|████▍ | 129/291 [00:03<00:04, 38.60it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 37.80it/s] Loading 0: 47%|████▋ | 138/291 [00:03<00:03, 39.30it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:04, 35.81it/s] Loading 0: 51%|█████ | 147/291 [00:03<00:03, 38.96it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:03, 38.48it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 41.57it/s] Loading 0: 55%|█████▌ | 161/291 [00:04<00:03, 42.32it/s] Loading 0: 57%|█████▋ | 166/291 [00:04<00:02, 43.13it/s] Loading 0: 59%|█████▉ | 171/291 [00:04<00:02, 44.22it/s] Loading 0: 60%|██████ | 176/291 [00:04<00:02, 44.30it/s] Loading 0: 62%|██████▏ | 181/291 [00:04<00:03, 35.36it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:03, 30.75it/s] Loading 0: 66%|██████▌ | 191/291 [00:05<00:03, 31.80it/s] Loading 0: 67%|██████▋ | 195/291 [00:05<00:02, 32.20it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:02, 39.90it/s] Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 40.97it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:01, 41.10it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 45.99it/s] Loading 0: 77%|███████▋ | 225/291 [00:05<00:01, 46.47it/s] Loading 0: 79%|███████▉ | 230/291 [00:06<00:01, 37.50it/s] Loading 0: 81%|████████▏ | 237/291 [00:06<00:01, 43.45it/s] Loading 0: 83%|████████▎ | 242/291 [00:06<00:01, 43.56it/s] Loading 0: 85%|████████▍ | 247/291 [00:06<00:00, 44.14it/s] Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 42.18it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 40.79it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 45.82it/s] Loading 0: 93%|█████████▎| 270/291 [00:06<00:00, 46.73it/s] Loading 0: 95%|█████████▍| 275/291 [00:07<00:00, 37.24it/s] Loading 0: 97%|█████████▋| 281/291 [00:07<00:00, 42.11it/s] Loading 0: 98%|█████████▊| 286/291 [00:07<00:00, 39.46it/s] Loading 0: 100%|██████████| 291/291 [00:12<00:00, 3.03it/s]
Job cycy233-model3-7-v1-mkmlizer completed after 83.65s with status: succeeded
Stopping job with name cycy233-model3-7-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model3-7-v1
Waiting for inference service cycy233-model3-7-v1 to be ready
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cycy233-model3-7-v1 ready after 160.5850019454956s
Pipeline stage MKMLDeployer completed in 161.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.198152542114258s
Received healthy response to inference request in 1.1860647201538086s
Received healthy response to inference request in 1.241133451461792s
Received healthy response to inference request in 1.1945691108703613s
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 1.1820580959320068s
5 requests
0 failed requests
5th percentile: 1.1828594207763672
10th percentile: 1.1836607456207275
20th percentile: 1.1852633953094482
30th percentile: 1.1877655982971191
40th percentile: 1.1911673545837402
50th percentile: 1.1945691108703613
60th percentile: 1.2131948471069336
70th percentile: 1.2318205833435059
80th percentile: 1.4325372695922853
90th percentile: 1.8153449058532716
95th percentile: 2.0067487239837645
99th percentile: 2.159871778488159
mean time: 1.4003955841064453
Pipeline stage StressChecker completed in 8.41s
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 0.94s
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 0.74s
Shutdown handler de-registered
cycy233-model3-7_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-model3-7-v1-profiler
Waiting for inference service cycy233-model3-7-v1-profiler to be ready
Inference service cycy233-model3-7-v1-profiler ready after 160.61925339698792s
Pipeline stage MKMLProfilerDeployer completed in 161.03s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-model3-7-v1-profiler-predictor-00001-deployment-75wrlvx:/code/chaiverse_profiler_1740734629 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-model3-7-v1-profiler-predictor-00001-deployment-75wrlvx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1740734629 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1740734629/summary.json'
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 2123.01s
Shutdown handler de-registered
cycy233-model3-7_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model3-7_v1 status is now torndown due to DeploymentManager action