submission_id: trace2333-mistral-trail10_v2
developer_uid: Trace2333
best_of: 8
celo_rating: 1233.43
display_name: trace2333-mistral-trail10_v2
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': 0.06, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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_trail10
latencies: [{'batch_size': 1, 'throughput': 0.6885034304047856, 'latency_mean': 1.452329066991806, 'latency_p50': 1.457390308380127, 'latency_p90': 1.6127994537353516}, {'batch_size': 3, 'throughput': 1.3344026891107537, 'latency_mean': 2.234913127422333, 'latency_p50': 2.2388155460357666, 'latency_p90': 2.469950795173645}, {'batch_size': 5, 'throughput': 1.578073979682442, 'latency_mean': 3.1516580986976623, 'latency_p50': 3.1607401371002197, 'latency_p90': 3.5911274433135985}, {'batch_size': 6, 'throughput': 1.622473037789041, 'latency_mean': 3.6750342512130736, 'latency_p50': 3.669044613838196, 'latency_p90': 4.189917254447937}, {'batch_size': 8, 'throughput': 1.6077859344873568, 'latency_mean': 4.941626864671707, 'latency_p50': 4.896738648414612, 'latency_p90': 5.676589632034302}, {'batch_size': 10, 'throughput': 1.5518976264029087, 'latency_mean': 6.402112463712692, 'latency_p50': 6.411877989768982, 'latency_p90': 7.298997926712036}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trail1
model_name: trace2333-mistral-trail10_v2
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trail10
model_size: 13B
num_battles: 12809
num_wins: 6194
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.63
timestamp: 2024-09-11T12:45:14+00:00
us_pacific_date: 2024-09-11
win_ratio: 0.4835662424857522
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-trail10-v2-mkmlizer
Waiting for job on trace2333-mistral-trail10-v2-mkmlizer to finish
trace2333-mistral-trail10-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trail10-v2-mkmlizer: ║ _____ __ __ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-mistral-trail10-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-mistral-trail10-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ /___/ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Version: 0.10.1 ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-mistral-trail10-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-mistral-trail10-v2-mkmlizer: ║ belonging to: ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_henub_2024-09-09: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44160->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
trace2333-mistral-trail10-v2-mkmlizer: Downloaded to shared memory in 34.935s
trace2333-mistral-trail10-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg_7x_omt, device:0
trace2333-mistral-trail10-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trail10-v2-mkmlizer: quantized model in 35.795s
trace2333-mistral-trail10-v2-mkmlizer: Processed model Trace2333/mistral_trail10 in 70.730s
trace2333-mistral-trail10-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trail10-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trail10-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trail10-v2
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/config.json
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/special_tokens_map.json
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/tokenizer_config.json
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/tokenizer.json
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
Stopping job with name trace2333-mistral-trail10-v2-mkmlizer
%s, retrying in %s seconds...
Stopping job with name trace2333-mistral-trail10-v2-mkmlizer
%s, retrying in %s seconds...
Stopping job with name trace2333-mistral-trail10-v2-mkmlizer
Retrying (%r) after connection broken by '%r': %s
%s, retrying in %s seconds...
Starting job with name trace2333-mistral-trail10-v2-mkmlizer
Waiting for job on trace2333-mistral-trail10-v2-mkmlizer to finish
trace2333-mistral-trail10-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trail10-v2-mkmlizer: ║ _____ __ __ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-mistral-trail10-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-mistral-trail10-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ /___/ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Version: 0.10.1 ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-mistral-trail10-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-mistral-trail10-v2-mkmlizer: ║ belonging to: ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-mistral-trail10-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-mistral-trail10-v2-mkmlizer: ║ ║
trace2333-mistral-trail10-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Stopping job with name trace2333-mistral-trail10-v2-mkmlizer
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
%s, retrying in %s seconds...
Starting job with name trace2333-mistral-trail10-v2-mkmlizer
Waiting for job on trace2333-mistral-trail10-v2-mkmlizer to finish
trace2333-mistral-trail10-v2-mkmlizer: quantized model in 36.326s
trace2333-mistral-trail10-v2-mkmlizer: Processed model Trace2333/mistral_trail10 in 62.334s
trace2333-mistral-trail10-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trail10-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trail10-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trail10-v2
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/config.json
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/special_tokens_map.json
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/tokenizer_config.json
trace2333-mistral-trail10-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trail10-v2/tokenizer.json
trace2333-mistral-trail10-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:07, 45.84it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:05, 66.39it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:05, 64.40it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:04, 69.53it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 71.33it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:04, 73.94it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:15, 19.58it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 25.41it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.25it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 37.83it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 45.61it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 51.35it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 56.20it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 62.53it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 67.10it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:10, 20.38it/s] Loading 0: 42%|████▏ | 152/363 [00:04<00:07, 27.40it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.65it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 39.51it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:03, 48.95it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 52.56it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 58.15it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 59.16it/s] Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 63.95it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:06, 20.07it/s] Loading 0: 64%|██████▍ | 233/363 [00:06<00:04, 27.06it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 33.97it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 38.30it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 44.55it/s] Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 48.97it/s] Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 55.26it/s] Loading 0: 79%|███████▉ | 286/363 [00:06<00:01, 59.60it/s] Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 66.16it/s] Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 20.61it/s] Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 26.31it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 32.69it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 38.77it/s] Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 46.34it/s] Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 53.08it/s] Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 56.73it/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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job trace2333-mistral-trail10-v2-mkmlizer completed after 192.62s with status: succeeded
Stopping job with name trace2333-mistral-trail10-v2-mkmlizer
Pipeline stage MKMLizer completed in 420.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trail10-v2
Waiting for inference service trace2333-mistral-trail10-v2 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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-mistral-trail10-v2 ready after 161.0333743095398s
Pipeline stage MKMLDeployer completed in 161.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.8470888137817383s
Received healthy response to inference request in 1.950272560119629s
Received healthy response to inference request in 2.2921791076660156s
Received healthy response to inference request in 1.6620125770568848s
Received healthy response to inference request in 1.7891123294830322s
5 requests
0 failed requests
5th percentile: 1.6874325275421143
10th percentile: 1.7128524780273438
20th percentile: 1.7636923789978027
30th percentile: 1.8213443756103516
40th percentile: 1.8858084678649902
50th percentile: 1.950272560119629
60th percentile: 2.0870351791381836
70th percentile: 2.2237977981567383
80th percentile: 2.6031610488891603
90th percentile: 3.2251249313354493
95th percentile: 3.5361068725585936
99th percentile: 3.7848924255371093
mean time: 2.30813307762146
Pipeline stage StressChecker completed in 13.92s
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 12.24s
Shutdown handler de-registered
trace2333-mistral-trail10_v2 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trail10-v2-profiler
Waiting for inference service trace2333-mistral-trail10-v2-profiler to be ready
Inference service trace2333-mistral-trail10-v2-profiler ready after 160.3694806098938s
Pipeline stage MKMLProfilerDeployer completed in 160.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-tr8290ac086bcc8f202f836e29e5bb5ac6-deplo25j2v:/code/chaiverse_profiler_1726059525 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-tr8290ac086bcc8f202f836e29e5bb5ac6-deplo25j2v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726059525 && 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_1726059525/summary.json'
kubectl exec -it trace2333-mistral-tr8290ac086bcc8f202f836e29e5bb5ac6-deplo25j2v --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726059525/summary.json'
Pipeline stage MKMLProfilerRunner completed in 949.69s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trail10-v2-profiler is running
Tearing down inference service trace2333-mistral-trail10-v2-profiler
Service trace2333-mistral-trail10-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
Shutdown handler de-registered
trace2333-mistral-trail10_v2 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trail10_v2 status is now torndown due to DeploymentManager action