trace2333-mistral-trail7

developer_uid: Trace2333

submission_id: trace2333-mistral-trail7_v1

model_name: trace2333-mistral-trail7_v1

model_group: Trace2333/mistral_trail7

status: torndown

timestamp: 2024-09-10T08:08:36+00:00

num_battles: 12416

num_wins: 6850

celo_rating: 1248.88

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/mistral_trail7

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6909249641691841, 'latency_mean': 1.4472738909721374, 'latency_p50': 1.4514127969741821, 'latency_p90': 1.6068835735321045}, {'batch_size': 3, 'throughput': 1.3154677925230294, 'latency_mean': 2.27214830994606, 'latency_p50': 2.2674163579940796, 'latency_p90': 2.541661238670349}, {'batch_size': 5, 'throughput': 1.5485499386738923, 'latency_mean': 3.210911228656769, 'latency_p50': 3.2282934188842773, 'latency_p90': 3.6303738832473753}, {'batch_size': 6, 'throughput': 1.595131612608219, 'latency_mean': 3.7317805922031404, 'latency_p50': 3.770570993423462, 'latency_p90': 4.208651399612426}, {'batch_size': 8, 'throughput': 1.5578012555242922, 'latency_mean': 5.088054132461548, 'latency_p50': 5.106116890907288, 'latency_p90': 5.777674531936645}, {'batch_size': 10, 'throughput': 1.5360011540633671, 'latency_mean': 6.474262558221817, 'latency_p50': 6.472724676132202, 'latency_p90': 7.403953194618225}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: trace2333-mistral-trail7_v1

is_internal_developer: False

language_model: Trace2333/mistral_trail7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.61

us_pacific_date: 2024-09-10

win_ratio: 0.5517074742268041

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-trail7-v1-mkmlizer
Waiting for job on trace2333-mistral-trail7-v1-mkmlizer to finish
trace2333-mistral-trail7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trail7-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trail7-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trail7-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trail7-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trail7-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trail7-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail7-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trail7-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trail7-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trail7-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail7-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trail7-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trail7-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail7-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trail7-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trail7-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trail7-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trail7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57792->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission blend_hokok_2024-09-09: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
trace2333-mistral-trail7-v1-mkmlizer: Downloaded to shared memory in 43.998s
trace2333-mistral-trail7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsmz6y7__, device:0
trace2333-mistral-trail7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trail7-v1-mkmlizer: quantized model in 36.891s
trace2333-mistral-trail7-v1-mkmlizer: Processed model Trace2333/mistral_trail7 in 80.889s
trace2333-mistral-trail7-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trail7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trail7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trail7-v1
trace2333-mistral-trail7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trail7-v1/config.json
trace2333-mistral-trail7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trail7-v1/special_tokens_map.json
trace2333-mistral-trail7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trail7-v1/tokenizer_config.json
trace2333-mistral-trail7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trail7-v1/tokenizer.json
trace2333-mistral-trail7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trail7-v1/flywheel_model.0.safetensors
trace2333-mistral-trail7-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 48.26it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 68.35it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 86.25it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:04, 79.12it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:04, 77.39it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 78.04it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:14, 20.20it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:12, 23.24it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.37it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 34.87it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 42.23it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 49.75it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 56.24it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:04, 58.21it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 61.32it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 19.81it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.45it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.13it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 38.09it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 44.13it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 51.13it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 56.80it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 59.90it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 61.12it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:07, 19.69it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.15it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 31.61it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 38.64it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 45.15it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 52.34it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 57.31it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 63.22it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:00, 68.05it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.92it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.24it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 32.52it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 39.35it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 45.57it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 48.57it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 53.01it/s]
                                                            
Job trace2333-mistral-trail7-v1-mkmlizer completed after 104.65s with status: succeeded
Stopping job with name trace2333-mistral-trail7-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.83s
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-trail7-v1
Waiting for inference service trace2333-mistral-trail7-v1 to be ready
Failed to get response for submission rica40325-feedback-dpo-4_v1: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:49758->127.0.0.1:8080: write tcp 127.0.0.1:49758->127.0.0.1:8080: use of closed network connection\n')
Failed to get response for submission blend_fedek_2024-08-24: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-mistral-trail7-v1 ready after 160.9070451259613s
Pipeline stage MKMLDeployer completed in 161.29s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission blend_sanen_2024-09-09: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52392->127.0.0.1:8080: read: connection reset by peer\n')
Received healthy response to inference request in 3.2140920162200928s
Received healthy response to inference request in 1.6465404033660889s
Received healthy response to inference request in 2.4270832538604736s
Received healthy response to inference request in 1.6755766868591309s
Received healthy response to inference request in 2.1776254177093506s
5 requests
0 failed requests
5th percentile: 1.6523476600646974
10th percentile: 1.6581549167633056
20th percentile: 1.6697694301605224
30th percentile: 1.7759864330291748
40th percentile: 1.9768059253692627
50th percentile: 2.1776254177093506
60th percentile: 2.2774085521698
70th percentile: 2.377191686630249
80th percentile: 2.5844850063323976
90th percentile: 2.899288511276245
95th percentile: 3.0566902637481688
99th percentile: 3.182611665725708
mean time: 2.228183555603027
Pipeline stage StressChecker completed in 12.40s
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 8.54s
Shutdown handler de-registered
trace2333-mistral-trail7_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trail7-v1-profiler
Waiting for inference service trace2333-mistral-trail7-v1-profiler to be ready
Inference service trace2333-mistral-trail7-v1-profiler ready after 150.36160564422607s
Pipeline stage MKMLProfilerDeployer completed in 150.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trail7-v1-profiler-predictor-00001-deplotlq7l:/code/chaiverse_profiler_1725956199 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trail7-v1-profiler-predictor-00001-deplotlq7l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725956199 && 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_1725956199/summary.json'
kubectl exec -it trace2333-mistral-trail7-v1-profiler-predictor-00001-deplotlq7l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725956199/summary.json'
Pipeline stage MKMLProfilerRunner completed in 960.05s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trail7-v1-profiler is running
Tearing down inference service trace2333-mistral-trail7-v1-profiler
Service trace2333-mistral-trail7-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.70s
Shutdown handler de-registered
trace2333-mistral-trail7_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trail7_v1 status is now torndown due to DeploymentManager action