trace2333-mistral-trail8

submission_id: trace2333-mistral-trail8_v4

developer_uid: Trace2333

alignment_samples: 12322

alignment_score: -0.23273946345224358

best_of: 8

celo_rating: 1248.85

display_name: trace2333-mistral-trail8_v4

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', '</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_trail8

latencies: [{'batch_size': 1, 'throughput': 0.6929173692034323, 'latency_mean': 1.4430825316905975, 'latency_p50': 1.448025107383728, 'latency_p90': 1.5930598735809327}, {'batch_size': 3, 'throughput': 1.3214948433071112, 'latency_mean': 2.259841080904007, 'latency_p50': 2.2671138048171997, 'latency_p90': 2.513117218017578}, {'batch_size': 5, 'throughput': 1.5404837479431772, 'latency_mean': 3.2296933555603027, 'latency_p50': 3.2353299856185913, 'latency_p90': 3.6069010972976683}, {'batch_size': 6, 'throughput': 1.5826015345801907, 'latency_mean': 3.770652008056641, 'latency_p50': 3.8118597269058228, 'latency_p90': 4.220084023475647}, {'batch_size': 8, 'throughput': 1.5952745959958958, 'latency_mean': 4.993432296514511, 'latency_p50': 4.974144101142883, 'latency_p90': 5.698314046859741}, {'batch_size': 10, 'throughput': 1.543318015767306, 'latency_mean': 6.4384579336643215, 'latency_p50': 6.431819796562195, 'latency_p90': 7.34607560634613}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Trace2333/mistral_trail8

model_name: trace2333-mistral-trail8_v4

model_num_parameters: 12772070400.0

model_repo: Trace2333/mistral_trail8

model_size: 13B

num_battles: 12321

num_wins: 6458

propriety_score: 0.7513812154696132

propriety_total_count: 1086.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.59

timestamp: 2024-09-10T13:12:16+00:00

us_pacific_date: 2024-09-10

win_ratio: 0.5241457673890106

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-trail8-v4-mkmlizer
Waiting for job on trace2333-mistral-trail8-v4-mkmlizer to finish
trace2333-mistral-trail8-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trail8-v4-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trail8-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trail8-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trail8-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trail8-v4-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trail8-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trail8-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trail8-v4-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trail8-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trail8-v4-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trail8-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v4-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trail8-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trail8-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trail8-v4-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trail8-v4-mkmlizer: Downloaded to shared memory in 29.255s
trace2333-mistral-trail8-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgjjq15qg, device:0
trace2333-mistral-trail8-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trail8-v4-mkmlizer: quantized model in 35.509s
trace2333-mistral-trail8-v4-mkmlizer: Processed model Trace2333/mistral_trail8 in 64.764s
trace2333-mistral-trail8-v4-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trail8-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trail8-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trail8-v4
trace2333-mistral-trail8-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v4/config.json
trace2333-mistral-trail8-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v4/special_tokens_map.json
trace2333-mistral-trail8-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v4/tokenizer_config.json
trace2333-mistral-trail8-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trail8-v4/flywheel_model.0.safetensors
trace2333-mistral-trail8-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:08, 44.42it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 78.54it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:04, 81.16it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:03, 90.28it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 74.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:14, 21.10it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:10, 27.39it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 34.49it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 38.36it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.85it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 49.91it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 55.76it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 63.93it/s]
Loading 0:  37%|███▋      | 134/363 [00:02<00:03, 71.64it/s]
Loading 0:  39%|███▉      | 143/363 [00:03<00:09, 22.16it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 27.40it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 33.56it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:04, 40.45it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:03, 49.84it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 54.86it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 58.58it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 62.75it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 64.90it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:06, 20.82it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 26.56it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.58it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 41.22it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 50.66it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:01, 57.35it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 63.70it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 68.47it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:00, 68.80it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 20.60it/s]
Loading 0:  87%|████████▋ | 314/363 [00:07<00:01, 27.84it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.01it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.88it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 54.59it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 61.70it/s]
                                                            
Job trace2333-mistral-trail8-v4-mkmlizer completed after 84.01s with status: succeeded
Stopping job with name trace2333-mistral-trail8-v4-mkmlizer
Pipeline stage MKMLizer completed in 85.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trail8-v4
Waiting for inference service trace2333-mistral-trail8-v4 to be ready
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:32846->127.0.0.1:8080: read: connection reset by peer\n')
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-trail8-v4 ready after 160.5633466243744s
Pipeline stage MKMLDeployer completed in 161.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.864321231842041s
Received healthy response to inference request in 1.9966440200805664s
Received healthy response to inference request in 1.8186185359954834s
Received healthy response to inference request in 2.57088303565979s
Received healthy response to inference request in 1.6830849647521973s
5 requests
0 failed requests
5th percentile: 1.7101916790008544
10th percentile: 1.7372983932495116
20th percentile: 1.7915118217468262
30th percentile: 1.8542236328125
40th percentile: 1.9254338264465332
50th percentile: 1.9966440200805664
60th percentile: 2.2263396263122557
70th percentile: 2.4560352325439454
80th percentile: 2.6295706748962404
90th percentile: 2.7469459533691407
95th percentile: 2.8056335926055906
99th percentile: 2.852583703994751
mean time: 2.1867103576660156
Pipeline stage StressChecker completed in 12.10s
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 4.48s
Shutdown handler de-registered
trace2333-mistral-trail8_v4 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 trace2333-mistral-trail8-v4-profiler
Waiting for inference service trace2333-mistral-trail8-v4-profiler to be ready
Inference service trace2333-mistral-trail8-v4-profiler ready after 160.40913200378418s
Pipeline stage MKMLProfilerDeployer completed in 160.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trail8-v4-profiler-predictor-00001-deplo9pj5j:/code/chaiverse_profiler_1725974401 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trail8-v4-profiler-predictor-00001-deplo9pj5j --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725974401 && 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_1725974401/summary.json'
kubectl exec -it trace2333-mistral-trail8-v4-profiler-predictor-00001-deplo9pj5j --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725974401/summary.json'
Pipeline stage MKMLProfilerRunner completed in 956.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trail8-v4-profiler is running
Tearing down inference service trace2333-mistral-trail8-v4-profiler
Service trace2333-mistral-trail8-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
trace2333-mistral-trail8_v4 status is now inactive due to auto deactivation removed underperforming models