trace2333-mistral-trial6

developer_uid: Trace2333

submission_id: trace2333-mistral-trial6_v10

model_name: trace2333-mistral-trial6_v10

model_group: Trace2333/mistral_trial6

status: torndown

timestamp: 2024-09-07T05:25:29+00:00

num_battles: 12874

num_wins: 6826

celo_rating: 1261.62

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/mistral_trial6

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6949610859195114, 'latency_mean': 1.4388368475437163, 'latency_p50': 1.427449345588684, 'latency_p90': 1.6011191368103028}, {'batch_size': 3, 'throughput': 1.3470203872736604, 'latency_mean': 2.2202886736392973, 'latency_p50': 2.227669596672058, 'latency_p90': 2.4634252071380613}, {'batch_size': 5, 'throughput': 1.5950303581983445, 'latency_mean': 3.1201933109760285, 'latency_p50': 3.1003435850143433, 'latency_p90': 3.5682948350906374}, {'batch_size': 6, 'throughput': 1.633579756012557, 'latency_mean': 3.648024991750717, 'latency_p50': 3.652124524116516, 'latency_p90': 4.117176628112793}, {'batch_size': 8, 'throughput': 1.5955492075001416, 'latency_mean': 4.9776067745685575, 'latency_p50': 4.990996360778809, 'latency_p90': 5.740338850021362}, {'batch_size': 10, 'throughput': 1.5520498312352327, 'latency_mean': 6.397829188108444, 'latency_p50': 6.474210739135742, 'latency_p90': 7.238211727142334}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: trace2333-mistral-trial6_v10

is_internal_developer: False

language_model: Trace2333/mistral_trial6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2024-09-06

win_ratio: 0.5302159391020662

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}

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}

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-v10-mkmlizer
Waiting for job on trace2333-mistral-trial6-v10-mkmlizer to finish
trace2333-mistral-trial6-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v10-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial6-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial6-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial6-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial6-v10-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial6-v10-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v10-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial6-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial6-v10-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial6-v10-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial6-v10-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial6-v10-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v10-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial6-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial6-v10-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial6-v10-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-elo-alignment-run-3_v36: ('http://chaiml-elo-alignment-run-3-v36-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57266->127.0.0.1:8080: read: connection reset by peer\n')
trace2333-mistral-trial6-v10-mkmlizer: Downloaded to shared memory in 30.924s
trace2333-mistral-trial6-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6lefktcc, device:0
trace2333-mistral-trial6-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial6-v10-mkmlizer: quantized model in 35.632s
trace2333-mistral-trial6-v10-mkmlizer: Processed model Trace2333/mistral_trial6 in 66.556s
trace2333-mistral-trial6-v10-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v10
trace2333-mistral-trial6-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v10/config.json
trace2333-mistral-trial6-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v10/special_tokens_map.json
trace2333-mistral-trial6-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v10/tokenizer_config.json
trace2333-mistral-trial6-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v10/tokenizer.json
trace2333-mistral-trial6-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v10/flywheel_model.0.safetensors
trace2333-mistral-trial6-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 52.76it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:04, 75.71it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:04, 80.90it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:04, 78.48it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:03, 87.56it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 87.58it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:13, 21.61it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:10, 27.49it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:08, 34.61it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 49.13it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 56.77it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:03, 67.90it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:03, 70.15it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:02, 74.70it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:09, 21.83it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:07, 26.24it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:06, 32.78it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 39.18it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 46.88it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 54.45it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 59.50it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 65.58it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 70.83it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:06, 20.58it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:04, 26.15it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 32.54it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 39.94it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.16it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 52.87it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:01, 62.29it/s]
Loading 0:  81%|████████  | 293/363 [00:06<00:01, 65.17it/s]
Loading 0:  83%|████████▎ | 301/363 [00:06<00:00, 63.95it/s]
Loading 0:  85%|████████▌ | 309/363 [00:07<00:02, 20.98it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 27.31it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:01, 32.63it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 39.71it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 46.14it/s]
Loading 0:  98%|█████████▊| 355/363 [00:08<00:00, 49.86it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00,  4.28it/s]
                                                            
Job trace2333-mistral-trial6-v10-mkmlizer completed after 94.8s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v10-mkmlizer
Pipeline stage MKMLizer completed in 95.88s
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 trace2333-mistral-trial6-v10
Waiting for inference service trace2333-mistral-trial6-v10 to be ready
Failed to get response for submission blend_fedek_2024-08-24: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45810->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
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
Inference service trace2333-mistral-trial6-v10 ready after 150.4870674610138s
Pipeline stage MKMLDeployer completed in 151.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.513232469558716s
Received healthy response to inference request in 1.9823522567749023s
Received healthy response to inference request in 2.1170992851257324s
Received healthy response to inference request in 1.8443598747253418s
Received healthy response to inference request in 1.9629530906677246s
5 requests
0 failed requests
5th percentile: 1.8680785179138184
10th percentile: 1.891797161102295
20th percentile: 1.939234447479248
30th percentile: 1.9668329238891602
40th percentile: 1.9745925903320312
50th percentile: 1.9823522567749023
60th percentile: 2.0362510681152344
70th percentile: 2.0901498794555664
80th percentile: 2.196325922012329
90th percentile: 2.3547791957855226
95th percentile: 2.4340058326721192
99th percentile: 2.4973871421813967
mean time: 2.0839993953704834
Pipeline stage StressChecker completed in 11.51s
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 4.02s
Shutdown handler de-registered
trace2333-mistral-trial6_v10 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-v10-profiler
Waiting for inference service trace2333-mistral-trial6-v10-profiler to be ready
Inference service trace2333-mistral-trial6-v10-profiler ready after 140.33863496780396s
Pipeline stage MKMLProfilerDeployer completed in 140.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-tree98eabd680542f7bdf0f74b9b222f87-deplo6jkxs:/code/chaiverse_profiler_1725687178 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-tree98eabd680542f7bdf0f74b9b222f87-deplo6jkxs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725687178 && 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_1725687178/summary.json'
kubectl exec -it trace2333-mistral-tree98eabd680542f7bdf0f74b9b222f87-deplo6jkxs --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725687178/summary.json'
Pipeline stage MKMLProfilerRunner completed in 946.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v10-profiler is running
Tearing down inference service trace2333-mistral-trial6-v10-profiler
Service trace2333-mistral-trial6-v10-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.49s
Shutdown handler de-registered
trace2333-mistral-trial6_v10 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trial6_v10 status is now torndown due to DeploymentManager action