submission_id: cycy233-l3-p-v1-c4_v3
developer_uid: shiroe40
best_of: 4
celo_rating: 1228.36
display_name: auto
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/L3-p-v1-c4
latencies: [{'batch_size': 1, 'throughput': 1.0231328087676117, 'latency_mean': 0.9773284709453582, 'latency_p50': 0.971118688583374, 'latency_p90': 1.0945472717285156}, {'batch_size': 5, 'throughput': 3.0661866231981048, 'latency_mean': 1.6201731979846954, 'latency_p50': 1.627906322479248, 'latency_p90': 1.798301339149475}, {'batch_size': 10, 'throughput': 4.183002239060439, 'latency_mean': 2.369147003889084, 'latency_p50': 2.367402195930481, 'latency_p90': 2.6587594032287596}, {'batch_size': 15, 'throughput': 4.598835052806402, 'latency_mean': 3.2104713320732117, 'latency_p50': 3.1761468648910522, 'latency_p90': 3.682664108276367}, {'batch_size': 20, 'throughput': 4.8016917673205395, 'latency_mean': 4.101444087028503, 'latency_p50': 4.060888767242432, 'latency_p90': 4.723847723007202}, {'batch_size': 25, 'throughput': 4.898886297200419, 'latency_mean': 5.000938625335693, 'latency_p50': 5.007876038551331, 'latency_p90': 5.722132134437561}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v1-c4
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v1-c4
model_size: 8B
num_battles: 11833
num_wins: 5868
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 4.8
timestamp: 2024-09-10T10:19:57+00:00
us_pacific_date: 2024-09-10
win_ratio: 0.49590129299416885
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-l3-p-v1-c4-v3-mkmlizer
Waiting for job on cycy233-l3-p-v1-c4-v3-mkmlizer to finish
cycy233-l3-p-v1-c4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ /___/ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v1-c4-v3-mkmlizer: Downloaded to shared memory in 20.034s
cycy233-l3-p-v1-c4-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqbvrttte, device:0
cycy233-l3-p-v1-c4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v1-c4-v3-mkmlizer: quantized model in 25.779s
cycy233-l3-p-v1-c4-v3-mkmlizer: Processed model cycy233/L3-p-v1-c4 in 45.813s
cycy233-l3-p-v1-c4-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v1-c4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v1-c4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v3
cycy233-l3-p-v1-c4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v3/config.json
cycy233-l3-p-v1-c4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v3/special_tokens_map.json
cycy233-l3-p-v1-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v3/tokenizer_config.json
cycy233-l3-p-v1-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v3/tokenizer.json
cycy233-l3-p-v1-c4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v3/flywheel_model.0.safetensors
cycy233-l3-p-v1-c4-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 38.61it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 65.37it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 73.56it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 77.37it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 81.06it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 82.25it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 81.16it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 79.31it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 80.19it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 20.83it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:07, 26.21it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 32.57it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.13it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 46.88it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 54.20it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 61.25it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 67.14it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:01, 72.36it/s] Loading 0: 57%|█████▋ | 167/291 [00:03<00:01, 79.41it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:01, 80.88it/s] Loading 0: 64%|██████▍ | 186/291 [00:03<00:01, 85.78it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:04, 22.17it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:03, 28.19it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 34.53it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 41.61it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 48.47it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 55.75it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 61.34it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 64.87it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 69.91it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 72.76it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 74.16it/s]
Job cycy233-l3-p-v1-c4-v3-mkmlizer completed after 62.83s with status: succeeded
Stopping job with name cycy233-l3-p-v1-c4-v3-mkmlizer
Pipeline stage MKMLizer completed in 64.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v1-c4-v3
Waiting for inference service cycy233-l3-p-v1-c4-v3 to be ready
Inference service cycy233-l3-p-v1-c4-v3 ready after 161.5465133190155s
Pipeline stage MKMLDeployer completed in 161.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7728474140167236s
Received healthy response to inference request in 1.832592487335205s
Received healthy response to inference request in 1.856604814529419s
Received healthy response to inference request in 2.5556278228759766s
Received healthy response to inference request in 1.602330207824707s
5 requests
0 failed requests
5th percentile: 1.6364336490631104
10th percentile: 1.6705370903015138
20th percentile: 1.7387439727783203
30th percentile: 1.7847964286804199
40th percentile: 1.8086944580078126
50th percentile: 1.832592487335205
60th percentile: 1.8421974182128906
70th percentile: 1.8518023490905762
80th percentile: 1.9964094161987305
90th percentile: 2.2760186195373535
95th percentile: 2.415823221206665
99th percentile: 2.5276669025421143
mean time: 1.9240005493164063
Pipeline stage StressChecker completed in 10.37s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.75s
Shutdown handler de-registered
cycy233-l3-p-v1-c4_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v1-c4-v3-profiler
Waiting for inference service cycy233-l3-p-v1-c4-v3-profiler to be ready
Inference service cycy233-l3-p-v1-c4-v3-profiler ready after 150.3425009250641s
Pipeline stage MKMLProfilerDeployer completed in 150.69s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v1-c4-v3-profiler-predictor-00001-deployment-chrm8:/code/chaiverse_profiler_1725964038 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v1-c4-v3-profiler-predictor-00001-deployment-chrm8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725964038 && python profiles.py profile --best_of_n 4 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725964038/summary.json'
kubectl exec -it cycy233-l3-p-v1-c4-v3-profiler-predictor-00001-deployment-chrm8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725964038/summary.json'
Pipeline stage MKMLProfilerRunner completed in 440.20s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v1-c4-v3-profiler is running
Tearing down inference service cycy233-l3-p-v1-c4-v3-profiler
Service cycy233-l3-p-v1-c4-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.61s
Shutdown handler de-registered
cycy233-l3-p-v1-c4_v3 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-p-v1-c4_v3 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 3.17s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-l3-p-v1-c4_v3
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.31s
chaiml-virgo-edit-v1-1e5_v6 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 3.41s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 3.12s
admin requested tearing down of cycy233-l3-p-v1-c4_v4
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.04s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
chaiml-virgo-top-bots3x100-hr_v1 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-l3-p-v2-c1_v1
Running pipeline stage MKMLModelDeleter
Shutdown handler de-registered
chaiml-virgo-top-bots5x100-hr_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.75s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 3.66s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v2-c2_v1
chaiml-virgo-top-bots6x50-hr_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.94s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 3.62s
admin requested tearing down of cycy233-l3-p-v2-c3_v2
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
cycy233-l3-e-v0-c4_v5 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Pipeline stage MKMLDeleter completed in 3.70s
Pipeline stage MKMLModelDeleter completed in 3.47s
run pipeline stage %s
Shutdown handler de-registered
run pipeline %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-l3-p-v2-c4_v2
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
cycy233-l3-p-v1-c1_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.38s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
admin requested tearing down of cycy233-l3-p-v2_v1
Pipeline stage MKMLDeleter completed in 3.78s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c2_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.72s
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.70s
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c3_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
run pipeline %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.51s
Running pipeline stage MKMLDeleter
Pipeline stage MKMLDeleter completed in 3.26s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c4_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 3.42s
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of cycy233-l3-p-v3-c3_v1
Pipeline stage MKMLDeleter completed in 3.76s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.26s
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c4_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.29s
Running pipeline stage MKMLModelDeleter
run pipeline %s
run pipeline stage %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v3-c4_v1
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c4_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.29s
run pipeline %s
run pipeline stage %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v3-c4_v1
cycy233-l3-p-v1-c4_v3 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v3-c4_v1
Pipeline stage MKMLModelDeleter completed in 6.17s
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 6.00s
Running pipeline stage MKMLDeleter
cycy233-l3-p-v1-c4_v3 status is now torndown due to DeploymentManager action
run pipeline stage %s
run pipeline %s