submission_id: trace2333-mistral-trial6_v7
developer_uid: Trace2333
alignment_samples: 14548
alignment_score: 0.02857485248507466
best_of: 8
celo_rating: 1261.01
display_name: trace2333-mistral-trial6_v7
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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': 0.06, 'top_k': 80, '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: Trace2333/mistral_trial6
latencies: [{'batch_size': 1, 'throughput': 0.6891611665964446, 'latency_mean': 1.4509824657440185, 'latency_p50': 1.4452077150344849, 'latency_p90': 1.607437801361084}, {'batch_size': 3, 'throughput': 1.3441946731740373, 'latency_mean': 2.2250232231616973, 'latency_p50': 2.229312777519226, 'latency_p90': 2.4716946840286256}, {'batch_size': 5, 'throughput': 1.5641340828023147, 'latency_mean': 3.18346177816391, 'latency_p50': 3.178308367729187, 'latency_p90': 3.5676379919052126}, {'batch_size': 6, 'throughput': 1.6078715655514395, 'latency_mean': 3.70904011964798, 'latency_p50': 3.743173122406006, 'latency_p90': 4.233181715011597}, {'batch_size': 8, 'throughput': 1.6037938254895183, 'latency_mean': 4.958398458957672, 'latency_p50': 4.883913159370422, 'latency_p90': 5.682981610298157}, {'batch_size': 10, 'throughput': 1.5474590447320442, 'latency_mean': 6.430835030078888, 'latency_p50': 6.486454963684082, 'latency_p90': 7.308413767814636}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial6
model_name: trace2333-mistral-trial6_v7
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial6
model_size: 13B
num_battles: 14547
num_wins: 7866
propriety_score: 0.7456279809220986
propriety_total_count: 1258.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.62
timestamp: 2024-09-07T02:49:06+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5407300474324603
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 trace2333-mistral-trial6-v7-mkmlizer
Waiting for job on trace2333-mistral-trial6-v7-mkmlizer to finish
trace2333-mistral-trial6-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v7-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial6-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial6-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial6-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial6-v7-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial6-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v7-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial6-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial6-v7-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial6-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial6-v7-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial6-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v7-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial6-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial6-v7-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial6-v7-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial6-v7-mkmlizer: Downloaded to shared memory in 31.643s
trace2333-mistral-trial6-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvfty5bp4, device:0
trace2333-mistral-trial6-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-mistral-trial6-v7-mkmlizer: quantized model in 36.980s
trace2333-mistral-trial6-v7-mkmlizer: Processed model Trace2333/mistral_trial6 in 68.623s
trace2333-mistral-trial6-v7-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v7
trace2333-mistral-trial6-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v7/tokenizer.json
trace2333-mistral-trial6-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v7/flywheel_model.0.safetensors
trace2333-mistral-trial6-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 45.44it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:06, 57.43it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:05, 61.72it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:05, 60.92it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:05, 63.25it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:05, 59.38it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:17, 17.30it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 22.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.01it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 34.74it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 40.26it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 45.34it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 50.26it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:04, 53.10it/s]
Loading 0:  37%|███▋      | 133/363 [00:03<00:04, 57.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 19.10it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 24.28it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 30.11it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 36.51it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 41.28it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:03, 46.88it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:03, 51.25it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:02, 54.36it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 57.82it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:07, 19.29it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.06it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 31.26it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 37.04it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 42.41it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:01, 48.04it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:01, 50.80it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 53.06it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 62.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:03, 19.46it/s]
Loading 0:  86%|████████▌ | 313/363 [00:09<00:01, 25.35it/s]
Loading 0:  89%|████████▊ | 322/363 [00:09<00:01, 32.25it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 39.95it/s]
Loading 0:  94%|█████████▎| 340/363 [00:09<00:00, 46.76it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 53.78it/s]
Loading 0: 100%|██████████| 363/363 [00:15<00:00,  5.15it/s]
                                                            

Job trace2333-mistral-trial6-v7-mkmlizer completed after 104.83s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v7-mkmlizer
Pipeline stage MKMLizer completed in 106.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial6-v7
Waiting for inference service trace2333-mistral-trial6-v7 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-mistral-trial6-v7 ready after 140.69237327575684s
Pipeline stage MKMLDeployer completed in 141.91s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.1978845596313477s
Received healthy response to inference request in 1.3936948776245117s
Received healthy response to inference request in 1.7763481140136719s
Received healthy response to inference request in 2.1614434719085693s
Received healthy response to inference request in 1.9296841621398926s
5 requests
0 failed requests
5th percentile: 1.4702255249023437
10th percentile: 1.5467561721801757
20th percentile: 1.6998174667358399
30th percentile: 1.807015323638916
40th percentile: 1.8683497428894043
50th percentile: 1.9296841621398926
60th percentile: 2.022387886047363
70th percentile: 2.115091609954834
80th percentile: 2.168731689453125
90th percentile: 2.1833081245422363
95th percentile: 2.190596342086792
99th percentile: 2.1964269161224363
mean time: 1.8918110370635985
Pipeline stage StressChecker completed in 10.32s
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 6.10s
Shutdown handler de-registered
trace2333-mistral-trial6_v7 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 0.12s
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 trace2333-mistral-trial6-v7-profiler
Waiting for inference service trace2333-mistral-trial6-v7-profiler to be ready
Inference service trace2333-mistral-trial6-v7-profiler ready after 150.3598792552948s
Pipeline stage MKMLProfilerDeployer completed in 150.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial6-v7-profiler-predictor-00001-deplo6wfnt:/code/chaiverse_profiler_1725677798 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial6-v7-profiler-predictor-00001-deplo6wfnt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725677798 && 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_1725677798/summary.json'
kubectl exec -it trace2333-mistral-trial6-v7-profiler-predictor-00001-deplo6wfnt --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725677798/summary.json'
Pipeline stage MKMLProfilerRunner completed in 951.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v7-profiler is running
Tearing down inference service trace2333-mistral-trial6-v7-profiler
Service trace2333-mistral-trial6-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.61s
Shutdown handler de-registered
trace2333-mistral-trial6_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics