trace2333-mistral-trial6

submission_id: trace2333-mistral-trial6_v1

developer_uid: Trace2333

best_of: 8

celo_rating: 1262.74

display_name: trace2333-mistral-trial6_v1

family_friendly_score: 0.0

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': 0.9, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###'], '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': 0.6990706233852878, 'latency_mean': 1.4304055190086364, 'latency_p50': 1.435470700263977, 'latency_p90': 1.585783052444458}, {'batch_size': 3, 'throughput': 1.3321722253720152, 'latency_mean': 2.2463132309913636, 'latency_p50': 2.255096912384033, 'latency_p90': 2.4922226428985597}, {'batch_size': 5, 'throughput': 1.5505768763030705, 'latency_mean': 3.2035072052478792, 'latency_p50': 3.215604305267334, 'latency_p90': 3.593967866897583}, {'batch_size': 6, 'throughput': 1.5852401961077411, 'latency_mean': 3.763158547878265, 'latency_p50': 3.8212732076644897, 'latency_p90': 4.189141201972961}, {'batch_size': 8, 'throughput': 1.5857631714849059, 'latency_mean': 5.025874083042145, 'latency_p50': 5.065956234931946, 'latency_p90': 5.67856867313385}, {'batch_size': 10, 'throughput': 1.492962971325154, 'latency_mean': 6.650328783988953, 'latency_p50': 6.720650792121887, 'latency_p90': 7.514048409461975}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Trace2333/mistral_trial6

model_name: trace2333-mistral-trial6_v1

model_num_parameters: 12772070400.0

model_repo: Trace2333/mistral_trial6

model_size: 13B

num_battles: 12213

num_wins: 6477

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.59

timestamp: 2024-09-06T09:43:34+00:00

us_pacific_date: 2024-09-06

win_ratio: 0.5303365266519283

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-v1-mkmlizer
Waiting for job on trace2333-mistral-trial6-v1-mkmlizer to finish
trace2333-mistral-trial6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial6-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial6-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial6-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial6-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial6-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial6-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial6-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial6-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial6-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial6-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial6-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial6-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial6-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial6-v1-mkmlizer: Downloaded to shared memory in 46.431s
trace2333-mistral-trial6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_e1kgyl5, device:0
trace2333-mistral-trial6-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial6-v1-mkmlizer: quantized model in 36.186s
trace2333-mistral-trial6-v1-mkmlizer: Processed model Trace2333/mistral_trial6 in 82.617s
trace2333-mistral-trial6-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v1
trace2333-mistral-trial6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v1/config.json
trace2333-mistral-trial6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v1/special_tokens_map.json
trace2333-mistral-trial6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v1/tokenizer_config.json
trace2333-mistral-trial6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v1/tokenizer.json
trace2333-mistral-trial6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v1/flywheel_model.0.safetensors
trace2333-mistral-trial6-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 52.57it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 84.42it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:04, 78.78it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 82.24it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:03, 83.87it/s]
Loading 0:  17%|█▋        | 60/363 [00:00<00:03, 91.86it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:13, 21.00it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.56it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 34.68it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 39.54it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 46.75it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 53.63it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 60.61it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 67.08it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 20.24it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:08, 26.21it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.32it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 38.79it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 44.07it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 51.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 57.27it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 62.01it/s]
Loading 0:  59%|█████▉    | 215/363 [00:04<00:02, 70.33it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:06, 21.36it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 26.56it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 40.11it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 49.67it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 54.14it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 61.04it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 69.55it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:00, 73.95it/s]
Loading 0:  84%|████████▍ | 305/363 [00:07<00:02, 21.45it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.64it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.72it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 39.34it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 44.30it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 49.35it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 56.82it/s]
                                                            
Job trace2333-mistral-trial6-v1-mkmlizer completed after 104.88s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.68s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial6-v1
Waiting for inference service trace2333-mistral-trial6-v1 to be ready
Inference service trace2333-mistral-trial6-v1 ready after 151.03610014915466s
Pipeline stage MKMLDeployer completed in 152.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.773364782333374s
Received healthy response to inference request in 1.9229867458343506s
Received healthy response to inference request in 1.7980008125305176s
Received healthy response to inference request in 1.7166848182678223s
Received healthy response to inference request in 1.645782709121704s
5 requests
0 failed requests
5th percentile: 1.6599631309509277
10th percentile: 1.6741435527801514
20th percentile: 1.7025043964385986
30th percentile: 1.7329480171203613
40th percentile: 1.7654744148254395
50th percentile: 1.7980008125305176
60th percentile: 1.8479951858520507
70th percentile: 1.897989559173584
80th percentile: 2.0930623531341555
90th percentile: 2.4332135677337647
95th percentile: 2.603289175033569
99th percentile: 2.739349660873413
mean time: 1.9713639736175537
Pipeline stage StressChecker completed in 10.63s
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 9.24s
Shutdown handler de-registered
trace2333-mistral-trial6_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trial6-v1-profiler
Waiting for inference service trace2333-mistral-trial6-v1-profiler to be ready
Inference service trace2333-mistral-trial6-v1-profiler ready after 160.35725283622742s
Pipeline stage MKMLProfilerDeployer completed in 160.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial6-v1-profiler-predictor-00001-deplof9rnq:/code/chaiverse_profiler_1725616294 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial6-v1-profiler-predictor-00001-deplof9rnq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725616294 && 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_1725616294/summary.json'
kubectl exec -it trace2333-mistral-trial6-v1-profiler-predictor-00001-deplof9rnq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725616294/summary.json'
Pipeline stage MKMLProfilerRunner completed in 956.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v1-profiler is running
Tearing down inference service trace2333-mistral-trial6-v1-profiler
Service trace2333-mistral-trial6-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.60s
Shutdown handler de-registered
trace2333-mistral-trial6_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trial6_v1 status is now torndown due to DeploymentManager action