submission_id: trace2333-mistral-align-_5060_v1
developer_uid: Trace2333
best_of: 8
celo_rating: 1258.93
display_name: trace2333-mistral-align-_5060_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': 0.06, '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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Trace2333/mistral_align_namo_3982
latencies: [{'batch_size': 1, 'throughput': 0.6988125340664642, 'latency_mean': 1.4309403014183044, 'latency_p50': 1.429012656211853, 'latency_p90': 1.5985110998153687}, {'batch_size': 3, 'throughput': 1.3427863270572489, 'latency_mean': 2.23013707280159, 'latency_p50': 2.232988715171814, 'latency_p90': 2.482335662841797}, {'batch_size': 5, 'throughput': 1.5607376024064696, 'latency_mean': 3.1754097712039946, 'latency_p50': 3.1863008737564087, 'latency_p90': 3.5037932872772215}, {'batch_size': 6, 'throughput': 1.6119583389854915, 'latency_mean': 3.698821555376053, 'latency_p50': 3.6901440620422363, 'latency_p90': 4.082241153717041}, {'batch_size': 8, 'throughput': 1.6206327468075834, 'latency_mean': 4.909188275337219, 'latency_p50': 4.8911837339401245, 'latency_p90': 5.62070825099945}, {'batch_size': 10, 'throughput': 1.5630869157651222, 'latency_mean': 6.356412640810013, 'latency_p50': 6.337343335151672, 'latency_p90': 7.280079889297485}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_align_
model_name: trace2333-mistral-align-_5060_v1
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_align_namo_3982
model_size: 13B
num_battles: 12450
num_wins: 6702
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.62
timestamp: 2024-09-07T03:09:32+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5383132530120482
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-align-5060-v1-mkmlizer
Waiting for job on trace2333-mistral-align-5060-v1-mkmlizer to finish
trace2333-mistral-align-5060-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-align-5060-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-align-5060-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-align-5060-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-align-5060-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-align-5060-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-align-5060-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-align-5060-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-align-5060-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-align-5060-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-5060-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_susol_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45820->127.0.0.1:8080: read: connection reset by peer\n')
trace2333-mistral-align-5060-v1-mkmlizer: Downloaded to shared memory in 48.270s
trace2333-mistral-align-5060-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjqq_e76u, device:0
trace2333-mistral-align-5060-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-align-5060-v1-mkmlizer: quantized model in 37.029s
trace2333-mistral-align-5060-v1-mkmlizer: Processed model Trace2333/mistral_align_namo_3982 in 85.299s
trace2333-mistral-align-5060-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-align-5060-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-align-5060-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-align-5060-v1
trace2333-mistral-align-5060-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-align-5060-v1/config.json
trace2333-mistral-align-5060-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-align-5060-v1/special_tokens_map.json
trace2333-mistral-align-5060-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-align-5060-v1/tokenizer_config.json
trace2333-mistral-align-5060-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-align-5060-v1/flywheel_model.0.safetensors
trace2333-mistral-align-5060-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:08, 41.20it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:06, 53.58it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:05, 56.42it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:05, 63.11it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 68.13it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 65.66it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:16, 18.20it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.69it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.38it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 36.18it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 41.93it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 46.60it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 51.52it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:04, 58.14it/s]
Loading 0:  37%|███▋      | 133/363 [00:03<00:03, 59.36it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 19.71it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.20it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 30.91it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.72it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 42.53it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 49.96it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:03, 55.56it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:02, 56.93it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 61.46it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.28it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.52it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.31it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 37.59it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 43.99it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:01, 50.66it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:01, 55.61it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 61.81it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 63.48it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 19.88it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 25.18it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 30.78it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 37.24it/s]
Loading 0:  94%|█████████▎| 340/363 [00:09<00:00, 42.57it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 48.11it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 53.62it/s]
                                                            

Job trace2333-mistral-align-5060-v1-mkmlizer completed after 105.34s with status: succeeded
Stopping job with name trace2333-mistral-align-5060-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.30s
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 trace2333-mistral-align-5060-v1
Waiting for inference service trace2333-mistral-align-5060-v1 to be ready
Failed to get response for submission neversleep-noromaid-v0_8068_v150: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39398->127.0.0.1:8080: read: connection reset by peer\n')
Inference service trace2333-mistral-align-5060-v1 ready after 150.72178053855896s
Pipeline stage MKMLDeployer completed in 151.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3192052841186523s
Received healthy response to inference request in 1.9423298835754395s
Received healthy response to inference request in 1.7206752300262451s
Received healthy response to inference request in 1.7909460067749023s
Received healthy response to inference request in 2.00365948677063s
5 requests
0 failed requests
5th percentile: 1.7347293853759767
10th percentile: 1.748783540725708
20th percentile: 1.7768918514251708
30th percentile: 1.8212227821350098
40th percentile: 1.8817763328552246
50th percentile: 1.9423298835754395
60th percentile: 1.9668617248535156
70th percentile: 1.9913935661315918
80th percentile: 2.0667686462402344
90th percentile: 2.1929869651794434
95th percentile: 2.256096124649048
99th percentile: 2.3065834522247313
mean time: 1.9553631782531737
Pipeline stage StressChecker completed in 11.02s
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 5.31s
Shutdown handler de-registered
trace2333-mistral-align-_5060_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 0.10s
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 trace2333-mistral-align-5060-v1-profiler
Waiting for inference service trace2333-mistral-align-5060-v1-profiler to be ready
Inference service trace2333-mistral-align-5060-v1-profiler ready after 150.39126706123352s
Pipeline stage MKMLProfilerDeployer completed in 150.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-ale18dd2cb6535f9cdb6d6bb6092436ac4-deploxmmzj:/code/chaiverse_profiler_1725679034 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-ale18dd2cb6535f9cdb6d6bb6092436ac4-deploxmmzj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725679034 && 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_1725679034/summary.json'
kubectl exec -it trace2333-mistral-ale18dd2cb6535f9cdb6d6bb6092436ac4-deploxmmzj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725679034/summary.json'
Pipeline stage MKMLProfilerRunner completed in 944.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-align-5060-v1-profiler is running
Tearing down inference service trace2333-mistral-align-5060-v1-profiler
Service trace2333-mistral-align-5060-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.48s
Shutdown handler de-registered
trace2333-mistral-align-_5060_v1 status is now inactive due to auto deactivation removed underperforming models
run pipeline %s
admin requested tearing down of trace2333-mistral-align-_5060_v1
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
Shutdown handler de-registered
trace2333-mistral-align-_5060_v1 status is now torndown due to DeploymentManager action