developer_uid: azuruce
submission_id: nothingiisreal-mn-12b-st_5165_v1
model_name: nothingiisreal-mn-12b-st_5165_v1
model_group: nothingiisreal/MN-12B-St
status: torndown
timestamp: 2024-09-24T21:09:06+00:00
num_battles: 4579
num_wins: 2440
celo_rating: 1277.06
family_friendly_score: 0.0
submission_type: basic
model_repo: nothingiisreal/MN-12B-Starcannon-v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6103152526934317, 'latency_mean': 1.6383972156047821, 'latency_p50': 1.6388707160949707, 'latency_p90': 1.7957501411437988}, {'batch_size': 3, 'throughput': 1.0719469012249077, 'latency_mean': 2.7913889825344085, 'latency_p50': 2.8047813177108765, 'latency_p90': 3.0501055240631105}, {'batch_size': 5, 'throughput': 1.2084663557199427, 'latency_mean': 4.120880455970764, 'latency_p50': 4.138442158699036, 'latency_p90': 4.574367094039917}, {'batch_size': 6, 'throughput': 1.2405628595408345, 'latency_mean': 4.815910791158676, 'latency_p50': 4.834689259529114, 'latency_p90': 5.445346999168396}, {'batch_size': 8, 'throughput': 1.2326795543387585, 'latency_mean': 6.463274636268616, 'latency_p50': 6.496747732162476, 'latency_p90': 7.2970658302307125}, {'batch_size': 10, 'throughput': 1.2005956887383578, 'latency_mean': 8.288874335289002, 'latency_p50': 8.259465098381042, 'latency_p90': 9.46611499786377}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nothingiisreal-mn-12b-st_5165_v1
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: nothingiisreal/MN-12B-Starcannon-v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.18
us_pacific_date: 2024-09-24
win_ratio: 0.5328674383053068
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', '<|eot_id|>', '<|end_of_text|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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 nothingiisreal-mn-12b-st-5165-v1-mkmlizer
Waiting for job on nothingiisreal-mn-12b-st-5165-v1-mkmlizer to finish
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ _____ __ __ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ /___/ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ Version: 0.10.1 ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ https://mk1.ai ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ The license key for the current software has been verified as ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ belonging to: ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ Chai Research Corp. ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ║ ║
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: Downloaded to shared memory in 58.405s
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqbnxk6qj, device:0
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: quantized model in 34.945s
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: Processed model nothingiisreal/MN-12B-Starcannon-v2 in 93.350s
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: creating bucket guanaco-mkml-models
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/config.json
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/special_tokens_map.json
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/tokenizer_config.json
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/merges.txt
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/vocab.json
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/tokenizer.json
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nothingiisreal-mn-12b-st-5165-v1/flywheel_model.0.safetensors
nothingiisreal-mn-12b-st-5165-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:07, 3.01s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:49, 1.23it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:43, 3.39it/s] Loading 0: 6%|▌ | 20/363 [00:06<00:55, 6.15it/s] Loading 0: 7%|▋ | 25/363 [00:06<00:39, 8.56it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 13.10it/s] Loading 0: 10%|█ | 38/363 [00:06<00:18, 17.19it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 17.22it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 23.32it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 27.07it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 29.00it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 33.73it/s] Loading 0: 20%|█▉ | 72/363 [00:07<00:08, 35.29it/s] Loading 0: 21%|██ | 77/363 [00:07<00:07, 36.71it/s] Loading 0: 23%|██▎ | 82/363 [00:07<00:07, 39.58it/s] Loading 0: 24%|██▍ | 87/363 [00:08<00:07, 37.61it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:05, 46.47it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:05, 46.65it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:05, 43.97it/s] Loading 0: 31%|███ | 112/363 [00:08<00:05, 47.94it/s] Loading 0: 33%|███▎ | 118/363 [00:08<00:05, 48.48it/s] Loading 0: 34%|███▍ | 124/363 [00:08<00:07, 32.50it/s] Loading 0: 36%|███▌ | 131/363 [00:09<00:06, 38.11it/s] Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 40.38it/s] Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 41.02it/s] Loading 0: 41%|████ | 149/363 [00:09<00:04, 45.61it/s] Loading 0: 43%|████▎ | 155/363 [00:09<00:04, 45.94it/s] Loading 0: 44%|████▍ | 160/363 [00:09<00:04, 45.20it/s] Loading 0: 46%|████▌ | 167/363 [00:09<00:03, 49.68it/s] Loading 0: 48%|████▊ | 173/363 [00:09<00:04, 46.66it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 45.66it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 49.69it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 49.31it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 46.73it/s] Loading 0: 56%|█████▌ | 202/363 [00:10<00:04, 37.77it/s] Loading 0: 57%|█████▋ | 207/363 [00:10<00:03, 39.41it/s] Loading 0: 58%|█████▊ | 212/363 [00:10<00:03, 41.59it/s] Loading 0: 60%|██████ | 218/363 [00:11<00:03, 42.07it/s] Loading 0: 61%|██████▏ | 223/363 [00:11<00:03, 40.66it/s] Loading 0: 63%|██████▎ | 229/363 [00:11<00:02, 45.31it/s] Loading 0: 64%|██████▍ | 234/363 [00:11<00:02, 45.42it/s] Loading 0: 66%|██████▌ | 240/363 [00:11<00:02, 42.59it/s] Loading 0: 68%|██████▊ | 248/363 [00:11<00:02, 50.63it/s] Loading 0: 70%|██████▉ | 254/363 [00:11<00:02, 49.10it/s] Loading 0: 72%|███████▏ | 260/363 [00:11<00:02, 49.29it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:01, 51.70it/s] Loading 0: 75%|███████▍ | 272/363 [00:12<00:01, 49.56it/s] Loading 0: 77%|███████▋ | 278/363 [00:12<00:01, 48.96it/s] Loading 0: 78%|███████▊ | 283/363 [00:12<00:02, 37.57it/s] Loading 0: 79%|███████▉ | 288/363 [00:12<00:01, 39.33it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:01, 40.74it/s] Loading 0: 82%|████████▏ | 299/363 [00:12<00:01, 42.54it/s] Loading 0: 84%|████████▎ | 304/363 [00:12<00:01, 43.38it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 48.38it/s] Loading 0: 87%|████████▋ | 316/363 [00:13<00:00, 48.33it/s] Loading 0: 88%|████████▊ | 321/363 [00:13<00:01, 40.26it/s] Loading 0: 91%|█████████ | 329/363 [00:13<00:00, 48.69it/s] Loading 0: 92%|█████████▏| 335/363 [00:13<00:00, 46.52it/s] Loading 0: 94%|█████████▎| 340/363 [00:13<00:00, 45.65it/s] Loading 0: 96%|█████████▌| 347/363 [00:13<00:00, 50.47it/s] Loading 0: 97%|█████████▋| 353/363 [00:13<00:00, 49.64it/s] Loading 0: 99%|█████████▉| 359/363 [00:14<00:00, 50.19it/s]
Job nothingiisreal-mn-12b-st-5165-v1-mkmlizer completed after 122.92s with status: succeeded
Stopping job with name nothingiisreal-mn-12b-st-5165-v1-mkmlizer
Pipeline stage MKMLizer completed in 123.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nothingiisreal-mn-12b-st-5165-v1
Waiting for inference service nothingiisreal-mn-12b-st-5165-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service nothingiisreal-mn-12b-st-5165-v1 ready after 370.94371795654297s
Pipeline stage MKMLDeployer completed in 371.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.033700704574585s
Received healthy response to inference request in 3.4170541763305664s
Received healthy response to inference request in 3.647369623184204s
Received healthy response to inference request in 1.7711341381072998s
Received healthy response to inference request in 1.438035249710083s
5 requests
0 failed requests
5th percentile: 1.5046550273895263
10th percentile: 1.5712748050689698
20th percentile: 1.7045143604278565
30th percentile: 1.8236474514007568
40th percentile: 1.928674077987671
50th percentile: 2.033700704574585
60th percentile: 2.5870420932769775
70th percentile: 3.14038348197937
80th percentile: 3.463117265701294
90th percentile: 3.555243444442749
95th percentile: 3.6013065338134767
99th percentile: 3.6381570053100587
mean time: 2.4614587783813477
Pipeline stage StressChecker completed in 12.93s
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 4.70s
Shutdown handler de-registered
nothingiisreal-mn-12b-st_5165_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 0.11s
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 nothingiisreal-mn-12b-st-5165-v1-profiler
Waiting for inference service nothingiisreal-mn-12b-st-5165-v1-profiler to be ready
Inference service nothingiisreal-mn-12b-st-5165-v1-profiler ready after 210.53695607185364s
Pipeline stage MKMLProfilerDeployer completed in 210.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/nothingiisreal-mn-12a2866837879e64632a8a00d714e0c096-deplokkzjj:/code/chaiverse_profiler_1727212932 --namespace tenant-chaiml-guanaco
kubectl exec -it nothingiisreal-mn-12a2866837879e64632a8a00d714e0c096-deplokkzjj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727212932 && 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_1727212932/summary.json'
kubectl exec -it nothingiisreal-mn-12a2866837879e64632a8a00d714e0c096-deplokkzjj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727212932/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1175.06s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service nothingiisreal-mn-12b-st-5165-v1-profiler is running
Tearing down inference service nothingiisreal-mn-12b-st-5165-v1-profiler
Service nothingiisreal-mn-12b-st-5165-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.30s
Shutdown handler de-registered
nothingiisreal-mn-12b-st_5165_v1 status is now inactive due to auto deactivation removed underperforming models
nothingiisreal-mn-12b-st_5165_v1 status is now torndown due to DeploymentManager action