rica40325-mistral-3678

developer_uid: rica40325

submission_id: rica40325-mistral-3678_v3

model_name: rica40325-mistral-13b-2452_v1

model_group: rica40325/mistral-3678

status: torndown

timestamp: 2024-09-25T10:00:24+00:00

num_battles: 4151

num_wins: 2104

celo_rating: 1257.2

family_friendly_score: 0.5751430704155263

family_friendly_standard_error: 0.007773745379077283

submission_type: basic

model_repo: rica40325/mistral-3678

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6172480808986228, 'latency_mean': 1.6200324654579163, 'latency_p50': 1.6354018449783325, 'latency_p90': 1.7699403524398805}, {'batch_size': 3, 'throughput': 1.0970159328929867, 'latency_mean': 2.7258031272888186, 'latency_p50': 2.746163249015808, 'latency_p90': 3.0887904882431028}, {'batch_size': 5, 'throughput': 1.2310659801103683, 'latency_mean': 4.040990777015686, 'latency_p50': 4.026127219200134, 'latency_p90': 4.520905566215515}, {'batch_size': 6, 'throughput': 1.2581485800514112, 'latency_mean': 4.746298893690109, 'latency_p50': 4.7880260944366455, 'latency_p90': 5.294146108627319}, {'batch_size': 8, 'throughput': 1.2425358307555892, 'latency_mean': 6.398894253969193, 'latency_p50': 6.394856095314026, 'latency_p90': 7.231893396377563}, {'batch_size': 10, 'throughput': 1.2181474763794393, 'latency_mean': 8.158123362064362, 'latency_p50': 8.196940183639526, 'latency_p90': 9.286398911476136}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-mistral-13b-2452_v1

ineligible_reason: num_battles<5000

is_internal_developer: False

language_model: rica40325/mistral-3678

model_size: 13B

ranking_group: single

throughput_3p7s: 1.21

us_pacific_date: 2024-09-25

win_ratio: 0.5068658154661527

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', 'Bot:', 'User:', 'You:', 'Me:', '####'], 'max_input_tokens': 1024, '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 rica40325-mistral-3678-v3-mkmlizer
Waiting for job on rica40325-mistral-3678-v3-mkmlizer to finish
rica40325-mistral-3678-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-mistral-3678-v3-mkmlizer: ║     _____            __           __                                ║
rica40325-mistral-3678-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-mistral-3678-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-mistral-3678-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-mistral-3678-v3-mkmlizer: ║       /___/                                                         ║
rica40325-mistral-3678-v3-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
rica40325-mistral-3678-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-mistral-3678-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-mistral-3678-v3-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-mistral-3678-v3-mkmlizer: ║  belonging to:                                                      ║
rica40325-mistral-3678-v3-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-mistral-3678-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-mistral-3678-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-mistral-3678-v3-mkmlizer: ║                                                                     ║
rica40325-mistral-3678-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rica40325-mistral-3678-v3-mkmlizer: quantized model in 35.447s
rica40325-mistral-3678-v3-mkmlizer: Processed model rica40325/mistral-3678 in 62.678s
rica40325-mistral-3678-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-mistral-3678-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-mistral-3678-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-mistral-3678-v3
rica40325-mistral-3678-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-mistral-3678-v3/config.json
rica40325-mistral-3678-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-mistral-3678-v3/special_tokens_map.json
rica40325-mistral-3678-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-mistral-3678-v3/tokenizer_config.json
rica40325-mistral-3678-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-mistral-3678-v3/tokenizer.json
rica40325-mistral-3678-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-mistral-3678-v3/flywheel_model.0.safetensors
rica40325-mistral-3678-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 52.56it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:03, 86.47it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 86.15it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:03, 93.98it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:03, 85.71it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:13, 21.62it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 32.63it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:06, 40.63it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 46.78it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 53.10it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 59.83it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 64.79it/s]
Loading 0:  37%|███▋      | 134/363 [00:02<00:03, 72.44it/s]
Loading 0:  39%|███▉      | 143/363 [00:03<00:10, 21.92it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:06, 31.42it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:05, 38.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 45.83it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 52.36it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 65.13it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:02, 73.65it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:05, 23.58it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:04, 29.05it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 39.98it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 45.81it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:01, 53.95it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:01, 62.02it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 64.33it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:00, 68.75it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 22.58it/s]
Loading 0:  87%|████████▋ | 314/363 [00:07<00:01, 29.61it/s]
Loading 0:  89%|████████▊ | 322/363 [00:07<00:01, 35.08it/s]
Loading 0:  91%|█████████ | 331/363 [00:07<00:00, 42.44it/s]
Loading 0:  95%|█████████▍| 344/363 [00:07<00:00, 56.94it/s]
Loading 0:  98%|█████████▊| 355/363 [00:08<00:00, 61.92it/s]
                                                            
Job rica40325-mistral-3678-v3-mkmlizer completed after 86.2s with status: succeeded
Stopping job with name rica40325-mistral-3678-v3-mkmlizer
Pipeline stage MKMLizer completed in 87.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-mistral-3678-v3
Waiting for inference service rica40325-mistral-3678-v3 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
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 rica40325-mistral-3678-v3 ready after 211.24143958091736s
Pipeline stage MKMLDeployer completed in 211.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.444206953048706s
Received healthy response to inference request in 1.571094274520874s
Received healthy response to inference request in 2.1998772621154785s
Received healthy response to inference request in 2.843008518218994s
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
Received healthy response to inference request in 4.30990195274353s
5 requests
0 failed requests
5th percentile: 1.696850872039795
10th percentile: 1.8226074695587158
20th percentile: 2.0741206645965575
30th percentile: 2.248743200302124
40th percentile: 2.346475076675415
50th percentile: 2.444206953048706
60th percentile: 2.6037275791168213
70th percentile: 2.7632482051849365
80th percentile: 3.1363872051239015
90th percentile: 3.723144578933716
95th percentile: 4.0165232658386225
99th percentile: 4.251226215362549
mean time: 2.673617792129517
Pipeline stage StressChecker completed in 15.10s
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 6.22s
Shutdown handler de-registered
rica40325-mistral-3678_v3 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 rica40325-mistral-3678-v3-profiler
Waiting for inference service rica40325-mistral-3678-v3-profiler to be ready
Inference service rica40325-mistral-3678-v3-profiler ready after 220.4894061088562s
Pipeline stage MKMLProfilerDeployer completed in 220.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-mistral-3678-v3-profiler-predictor-00001-deploymcm9td:/code/chaiverse_profiler_1727259011 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-mistral-3678-v3-profiler-predictor-00001-deploymcm9td --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727259011 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727259011/summary.json'
kubectl exec -it rica40325-mistral-3678-v3-profiler-predictor-00001-deploymcm9td --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727259011/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-mistral-3678-v3-profiler is running
Tearing down inference service rica40325-mistral-3678-v3-profiler
Service rica40325-mistral-3678-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.53s
Shutdown handler de-registered
rica40325-mistral-3678_v3 status is now inactive due to auto deactivation removed underperforming models
rica40325-mistral-3678_v3 status is now torndown due to DeploymentManager action