submission_id: valentin87-duke-jack-dra_2042_v8
developer_uid: valentin87
alignment_samples: 11141
alignment_score: 0.053130891508076525
best_of: 8
celo_rating: 1231.04
display_name: valentin87-duke-jack-dra_2042_v8
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: valentin87/Duke_Jack_Dragonbane
latencies: [{'batch_size': 1, 'throughput': 0.696776070217777, 'latency_mean': 1.4351193773746491, 'latency_p50': 1.4245012998580933, 'latency_p90': 1.6007568120956421}, {'batch_size': 3, 'throughput': 1.3219200356636622, 'latency_mean': 2.262636765241623, 'latency_p50': 2.2722318172454834, 'latency_p90': 2.4884562730789184}, {'batch_size': 5, 'throughput': 1.5619650278140151, 'latency_mean': 3.1852872931957243, 'latency_p50': 3.196290612220764, 'latency_p90': 3.546238923072815}, {'batch_size': 6, 'throughput': 1.611953887824573, 'latency_mean': 3.696745674610138, 'latency_p50': 3.6783323287963867, 'latency_p90': 4.20354197025299}, {'batch_size': 8, 'throughput': 1.5907488781221335, 'latency_mean': 5.001939554214477, 'latency_p50': 4.984230995178223, 'latency_p90': 5.716370701789856}, {'batch_size': 10, 'throughput': 1.5424628137478094, 'latency_mean': 6.4413058841228485, 'latency_p50': 6.485933542251587, 'latency_p90': 7.3069655418396}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: valentin87/Duke_Jack_Dra
model_name: valentin87-duke-jack-dra_2042_v8
model_num_parameters: 12772070400.0
model_repo: valentin87/Duke_Jack_Dragonbane
model_size: 13B
num_battles: 11141
num_wins: 5368
propriety_score: 0.7314814814814815
propriety_total_count: 972.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.62
timestamp: 2024-09-12T11:00:17+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.4818238937258774
Download Preference Data
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 valentin87-duke-jack-dra-2042-v8-mkmlizer
Waiting for job on valentin87-duke-jack-dra-2042-v8-mkmlizer to finish
valentin87-duke-jack-dra-2042-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║     _____            __           __                                ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║       /___/                                                         ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  Version: 0.10.1                                                    ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  https://mk1.ai                                                     ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  belonging to:                                                      ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  Chai Research Corp.                                                ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ║                                                                     ║
valentin87-duke-jack-dra-2042-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-virgo-edit-v1-1e5_v12: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f1fca619940>, 'Connection to zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com timed out. (connect timeout=None)'))
valentin87-duke-jack-dra-2042-v8-mkmlizer: Downloaded to shared memory in 78.835s
valentin87-duke-jack-dra-2042-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoix5ueso, device:0
valentin87-duke-jack-dra-2042-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
valentin87-duke-jack-dra-2042-v8-mkmlizer: quantized model in 41.327s
valentin87-duke-jack-dra-2042-v8-mkmlizer: Processed model valentin87/Duke_Jack_Dragonbane in 120.162s
valentin87-duke-jack-dra-2042-v8-mkmlizer: creating bucket guanaco-mkml-models
valentin87-duke-jack-dra-2042-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
valentin87-duke-jack-dra-2042-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v8
valentin87-duke-jack-dra-2042-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v8/config.json
valentin87-duke-jack-dra-2042-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v8/special_tokens_map.json
valentin87-duke-jack-dra-2042-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v8/tokenizer_config.json
valentin87-duke-jack-dra-2042-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v8/tokenizer.json
valentin87-duke-jack-dra-2042-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/valentin87-duke-jack-dra-2042-v8/flywheel_model.0.safetensors
Job valentin87-duke-jack-dra-2042-v8-mkmlizer completed after 145.65s with status: succeeded
Stopping job with name valentin87-duke-jack-dra-2042-v8-mkmlizer
Pipeline stage MKMLizer completed in 147.63s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-duke-jack-dra-2042-v8
Waiting for inference service valentin87-duke-jack-dra-2042-v8 to be ready
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission zonemercy-virgo-edit-v1-1e5_v12: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f1fc314eea0>, 'Connection to zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com timed out. (connect timeout=None)'))
Inference service valentin87-duke-jack-dra-2042-v8 ready after 170.4925148487091s
Pipeline stage MKMLDeployer completed in 172.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4266111850738525s
Failed to get response for submission zonemercy-virgo-edit-v1-1e5_v12: HTTPConnectionPool(host='zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f2048839e50>, 'Connection to zonemercy-virgo-edit-v1-1e5-v12-predictor.tenant-chaiml-guanaco.k2.chaiverse.com timed out. (connect timeout=None)'))
Received healthy response to inference request in 6.9097535610198975s
Received healthy response to inference request in 1.9272313117980957s
Received healthy response to inference request in 4.948951005935669s
Received healthy response to inference request in 2.913989543914795s
5 requests
0 failed requests
5th percentile: 2.027107286453247
10th percentile: 2.1269832611083985
20th percentile: 2.3267352104187013
30th percentile: 2.524086856842041
40th percentile: 2.719038200378418
50th percentile: 2.913989543914795
60th percentile: 3.7279741287231443
70th percentile: 4.541958713531494
80th percentile: 5.341111516952515
90th percentile: 6.125432538986206
95th percentile: 6.517593050003051
99th percentile: 6.831321458816528
mean time: 3.825307321548462
Pipeline stage StressChecker completed in 23.22s
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 4.04s
Shutdown handler de-registered
valentin87-duke-jack-dra_2042_v8 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service valentin87-duke-jack-dra-2042-v8-profiler
Waiting for inference service valentin87-duke-jack-dra-2042-v8-profiler to be ready
Inference service valentin87-duke-jack-dra-2042-v8-profiler ready after 170.39482045173645s
Pipeline stage MKMLProfilerDeployer completed in 170.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-duke-jack77c46c73dd01174d27feaba1955ad193-deplokgxs4:/code/chaiverse_profiler_1726139379 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-duke-jack77c46c73dd01174d27feaba1955ad193-deplokgxs4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726139379 && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726139379/summary.json'
kubectl exec -it valentin87-duke-jack77c46c73dd01174d27feaba1955ad193-deplokgxs4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726139379/summary.json'
Pipeline stage MKMLProfilerRunner completed in 950.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-duke-jack-dra-2042-v8-profiler is running
Tearing down inference service valentin87-duke-jack-dra-2042-v8-profiler
Service valentin87-duke-jack-dra-2042-v8-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.74s
Shutdown handler de-registered
valentin87-duke-jack-dra_2042_v8 status is now inactive due to auto deactivation removed underperforming models