submission_id: mistralai-mistral-small-_5341_v1
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1234.9
display_name: mistralai-mistral-small-_5341_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': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
is_internal_developer: True
language_model: mistralai/Mistral-Small-Instruct-2409
latencies: [{'batch_size': 1, 'throughput': 0.38128104221954917, 'latency_mean': 2.6226805353164675, 'latency_p50': 2.63321316242218, 'latency_p90': 2.907293176651001}, {'batch_size': 2, 'throughput': 0.6078396423890761, 'latency_mean': 3.281096682548523, 'latency_p50': 3.2902787923812866, 'latency_p90': 3.641597557067871}, {'batch_size': 3, 'throughput': 0.7641835695850113, 'latency_mean': 3.917836228609085, 'latency_p50': 3.9227508306503296, 'latency_p90': 4.329065203666687}, {'batch_size': 4, 'throughput': 0.889898069447829, 'latency_mean': 4.479450694322586, 'latency_p50': 4.472897529602051, 'latency_p90': 4.971079874038696}, {'batch_size': 5, 'throughput': 0.9789218017866308, 'latency_mean': 5.081555757522583, 'latency_p50': 5.077998638153076, 'latency_p90': 5.606281328201294}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Small-
model_name: mistralai-mistral-small-_5341_v1
model_num_parameters: 22247282688.0
model_repo: mistralai/Mistral-Small-Instruct-2409
model_size: 22B
num_battles: 160561
num_wins: 74955
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.72
timestamp: 2024-09-17T19:15:28+00:00
us_pacific_date: 2024-09-17
win_ratio: 0.4668319205784717
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 mistralai-mistral-small-5341-v1-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v1-mkmlizer to finish
mistralai-mistral-small-5341-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v1-mkmlizer: ║ _____ __ __ ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ /___/ ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ Version: 0.10.1 ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ https://mk1.ai ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ The license key for the current software has been verified as ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ belonging to: ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ Chai Research Corp. ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
mistralai-mistral-small-5341-v1-mkmlizer: ║ ║
mistralai-mistral-small-5341-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-small-5341-v1-mkmlizer: Downloaded to shared memory in 137.348s
mistralai-mistral-small-5341-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxw9yh_cp, device:0
mistralai-mistral-small-5341-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-small-5341-v1-mkmlizer: quantized model in 51.875s
mistralai-mistral-small-5341-v1-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 189.223s
mistralai-mistral-small-5341-v1-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-small-5341-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-small-5341-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/special_tokens_map.json
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/config.json
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/tokenizer_config.json
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/tokenizer.model
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/tokenizer.json
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/flywheel_model.1.safetensors
mistralai-mistral-small-5341-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v1/flywheel_model.0.safetensors
mistralai-mistral-small-5341-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:16, 29.71it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:10, 46.37it/s] Loading 0: 4%|▎ | 18/507 [00:00<00:10, 44.74it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:13, 35.96it/s] Loading 0: 6%|▌ | 30/507 [00:00<00:11, 40.63it/s] Loading 0: 7%|▋ | 35/507 [00:00<00:12, 39.14it/s] Loading 0: 8%|▊ | 40/507 [00:01<00:11, 39.29it/s] Loading 0: 9%|▉ | 45/507 [00:01<00:11, 39.90it/s] Loading 0: 10%|▉ | 50/507 [00:01<00:13, 33.27it/s] Loading 0: 11%|█ | 54/507 [00:01<00:17, 25.60it/s] Loading 0: 11%|█ | 57/507 [00:01<00:17, 25.51it/s] Loading 0: 12%|█▏ | 63/507 [00:01<00:14, 31.38it/s] Loading 0: 13%|█▎ | 67/507 [00:01<00:13, 32.12it/s] Loading 0: 14%|█▍ | 72/507 [00:02<00:12, 35.34it/s] Loading 0: 15%|█▍ | 76/507 [00:02<00:11, 36.28it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:12, 33.69it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:10, 40.93it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:10, 40.27it/s] Loading 0: 19%|█▉ | 97/507 [00:02<00:10, 38.95it/s] Loading 0: 20%|█▉ | 101/507 [00:02<00:10, 38.24it/s] Loading 0: 21%|██ | 106/507 [00:02<00:10, 38.82it/s] Loading 0: 22%|██▏ | 111/507 [00:03<00:09, 40.60it/s] Loading 0: 23%|██▎ | 116/507 [00:03<00:15, 24.72it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:13, 28.23it/s] Loading 0: 25%|██▌ | 129/507 [00:03<00:10, 34.51it/s] Loading 0: 26%|██▋ | 134/507 [00:03<00:10, 35.16it/s] Loading 0: 27%|██▋ | 139/507 [00:03<00:10, 36.29it/s] Loading 0: 28%|██▊ | 143/507 [00:04<00:10, 36.22it/s] Loading 0: 29%|██▉ | 147/507 [00:04<00:09, 36.63it/s] Loading 0: 30%|██▉ | 151/507 [00:04<00:09, 35.91it/s] Loading 0: 31%|███ | 156/507 [00:04<00:09, 38.25it/s] Loading 0: 32%|███▏ | 160/507 [00:04<00:09, 37.24it/s] Loading 0: 32%|███▏ | 164/507 [00:04<00:09, 35.24it/s] Loading 0: 33%|███▎ | 169/507 [00:04<00:11, 28.36it/s] Loading 0: 34%|███▍ | 173/507 [00:05<00:11, 29.60it/s] Loading 0: 35%|███▍ | 177/507 [00:05<00:11, 28.57it/s] Loading 0: 36%|███▌ | 183/507 [00:05<00:09, 33.89it/s] Loading 0: 37%|███▋ | 187/507 [00:05<00:09, 33.91it/s] Loading 0: 38%|███▊ | 192/507 [00:05<00:08, 36.28it/s] Loading 0: 39%|███▊ | 196/507 [00:05<00:08, 35.93it/s] Loading 0: 40%|███▉ | 201/507 [00:05<00:08, 38.17it/s] Loading 0: 40%|████ | 205/507 [00:05<00:08, 36.97it/s] Loading 0: 41%|████▏ | 210/507 [00:06<00:07, 37.16it/s] Loading 0: 42%|████▏ | 214/507 [00:06<00:08, 35.28it/s] Loading 0: 43%|████▎ | 218/507 [00:06<00:08, 35.60it/s] Loading 0: 44%|████▍ | 222/507 [00:06<00:08, 35.58it/s] Loading 0: 45%|████▍ | 226/507 [00:06<00:10, 26.40it/s] Loading 0: 45%|████▌ | 230/507 [00:06<00:10, 26.61it/s] Loading 0: 47%|████▋ | 237/507 [00:06<00:07, 34.35it/s] Loading 0: 48%|████▊ | 241/507 [00:06<00:07, 34.31it/s] Loading 0: 49%|████▊ | 246/507 [00:07<00:07, 37.09it/s] Loading 0: 49%|████▉ | 250/507 [00:07<00:07, 34.67it/s] Loading 0: 50%|█████ | 255/507 [00:07<00:07, 35.50it/s] Loading 0: 51%|█████ | 259/507 [00:07<00:07, 34.57it/s] Loading 0: 52%|█████▏ | 264/507 [00:07<00:06, 36.74it/s] Loading 0: 53%|█████▎ | 268/507 [00:07<00:06, 35.01it/s] Loading 0: 54%|█████▍ | 273/507 [00:07<00:06, 37.15it/s] Loading 0: 55%|█████▍ | 277/507 [00:07<00:06, 35.15it/s] Loading 0: 56%|█████▌ | 282/507 [00:08<00:05, 38.91it/s] Loading 0: 56%|█████▋ | 286/507 [00:08<00:08, 26.64it/s] Loading 0: 57%|█████▋ | 290/507 [00:08<00:07, 28.86it/s] Loading 0: 58%|█████▊ | 294/507 [00:08<00:07, 28.45it/s] Loading 0: 59%|█████▉ | 298/507 [00:08<00:06, 30.93it/s] Loading 0: 59%|█████▉ | 299/507 [00:20<00:06, 30.93it/s] Loading 0: 59%|█████▉ | 300/507 [00:28<05:48, 1.68s/it] Loading 0: 60%|█████▉ | 302/507 [00:28<04:39, 1.37s/it] Loading 0: 61%|██████ | 307/507 [00:28<02:43, 1.23it/s] Loading 0: 61%|██████ | 310/507 [00:28<02:01, 1.62it/s] Loading 0: 62%|██████▏ | 314/507 [00:28<01:21, 2.38it/s] Loading 0: 63%|██████▎ | 318/507 [00:28<00:55, 3.39it/s] Loading 0: 64%|██████▎ | 322/507 [00:28<00:39, 4.70it/s] Loading 0: 64%|██████▍ | 327/507 [00:29<00:26, 6.92it/s] Loading 0: 65%|██████▌ | 331/507 [00:29<00:19, 8.95it/s] Loading 0: 66%|██████▌ | 335/507 [00:29<00:15, 11.35it/s] Loading 0: 67%|██████▋ | 340/507 [00:29<00:12, 13.08it/s] Loading 0: 68%|██████▊ | 343/507 [00:29<00:11, 14.59it/s] Loading 0: 68%|██████▊ | 347/507 [00:29<00:09, 16.87it/s] Loading 0: 70%|██████▉ | 354/507 [00:29<00:06, 23.86it/s] Loading 0: 71%|███████ | 358/507 [00:30<00:05, 25.93it/s] Loading 0: 72%|███████▏ | 363/507 [00:30<00:04, 29.94it/s] Loading 0: 72%|███████▏ | 367/507 [00:30<00:04, 30.89it/s] Loading 0: 73%|███████▎ | 372/507 [00:30<00:03, 33.88it/s] Loading 0: 74%|███████▍ | 376/507 [00:30<00:03, 33.02it/s] Loading 0: 75%|███████▌ | 381/507 [00:30<00:03, 35.02it/s] Loading 0: 76%|███████▌ | 385/507 [00:30<00:03, 35.10it/s] Loading 0: 77%|███████▋ | 389/507 [00:30<00:03, 35.48it/s] Loading 0: 78%|███████▊ | 393/507 [00:30<00:03, 34.95it/s] Loading 0: 78%|███████▊ | 397/507 [00:31<00:04, 26.37it/s] Loading 0: 79%|███████▉ | 401/507 [00:31<00:03, 26.56it/s] Loading 0: 80%|████████ | 407/507 [00:31<00:02, 33.82it/s] Loading 0: 81%|████████ | 411/507 [00:31<00:02, 32.22it/s] Loading 0: 82%|████████▏ | 415/507 [00:31<00:02, 33.60it/s] Loading 0: 83%|████████▎ | 419/507 [00:31<00:02, 31.15it/s] Loading 0: 84%|████████▍ | 426/507 [00:31<00:02, 39.13it/s] Loading 0: 85%|████████▌ | 431/507 [00:32<00:02, 37.47it/s] Loading 0: 86%|████████▌ | 435/507 [00:32<00:01, 36.66it/s] Loading 0: 87%|████████▋ | 439/507 [00:32<00:01, 35.57it/s] Loading 0: 88%|████████▊ | 444/507 [00:32<00:01, 38.11it/s] Loading 0: 88%|████████▊ | 448/507 [00:32<00:01, 35.68it/s] Loading 0: 90%|████████▉ | 454/507 [00:32<00:01, 37.35it/s] Loading 0: 90%|█████████ | 458/507 [00:34<00:08, 6.11it/s] Loading 0: 91%|█████████ | 461/507 [00:35<00:06, 7.32it/s] Loading 0: 92%|█████████▏| 465/507 [00:35<00:04, 9.36it/s] Loading 0: 93%|█████████▎| 472/507 [00:35<00:02, 14.55it/s] Loading 0: 94%|█████████▍| 476/507 [00:35<00:01, 17.05it/s] Loading 0: 95%|█████████▍| 481/507 [00:35<00:01, 21.21it/s] Loading 0: 96%|█████████▌| 485/507 [00:35<00:00, 23.40it/s] Loading 0: 97%|█████████▋| 490/507 [00:35<00:00, 27.64it/s] Loading 0: 97%|█████████▋| 494/507 [00:35<00:00, 28.44it/s] Loading 0: 98%|█████████▊| 499/507 [00:36<00:00, 32.22it/s] Loading 0: 99%|█████████▉| 503/507 [00:36<00:00, 32.69it/s]
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Job mistralai-mistral-small-5341-v1-mkmlizer completed after 221.84s with status: succeeded
Stopping job with name mistralai-mistral-small-5341-v1-mkmlizer
Pipeline stage MKMLizer completed in 222.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v1
Waiting for inference service mistralai-mistral-small-5341-v1 to be ready
Failed to get response for submission blend_tagim_2024-09-14: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54488->127.0.0.1:8080: read: connection reset by peer\n')
Inference service mistralai-mistral-small-5341-v1 ready after 222.47145223617554s
Pipeline stage MKMLDeployer completed in 222.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.638744354248047s
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 2.9559452533721924s
Received healthy response to inference request in 3.280493974685669s
Received healthy response to inference request in 2.0228607654571533s
Received healthy response to inference request in 2.6093599796295166s
5 requests
0 failed requests
5th percentile: 2.140160608291626
10th percentile: 2.2574604511260987
20th percentile: 2.492060136795044
30th percentile: 2.678677034378052
40th percentile: 2.817311143875122
50th percentile: 2.9559452533721924
60th percentile: 3.085764741897583
70th percentile: 3.2155842304229734
80th percentile: 3.352144050598145
90th percentile: 3.4954442024230956
95th percentile: 3.567094278335571
99th percentile: 3.624414339065552
mean time: 2.901480865478516
Pipeline stage StressChecker completed in 15.52s
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 6.58s
Shutdown handler de-registered
mistralai-mistral-small-_5341_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v1-profiler
Waiting for inference service mistralai-mistral-small-5341-v1-profiler to be ready
Inference service mistralai-mistral-small-5341-v1-profiler ready after 190.48633694648743s
Pipeline stage MKMLProfilerDeployer completed in 190.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sm4f289708a545463d36db46254434bd4e-deplojrvgv:/code/chaiverse_profiler_1726601231 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sm4f289708a545463d36db46254434bd4e-deplojrvgv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726601231 && 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_1726601231/summary.json'
kubectl exec -it mistralai-mistral-sm4f289708a545463d36db46254434bd4e-deplojrvgv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726601231/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1551.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v1-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v1-profiler
Service mistralai-mistral-small-5341-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
mistralai-mistral-small-_5341_v1 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small-_5341_v1 status is now torndown due to DeploymentManager action