trace2333-mistral-trial1

developer_uid: Trace2333
submission_id: trace2333-mistral-trial1_v1
model_name: trace2333-mistral-trial1_v1
model_group: Trace2333/mistral_trial1
status: torndown
timestamp: 2024-09-04T17:37:37+00:00
num_battles: 11035
num_wins: 5590
celo_rating: 1239.37
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/mistral_trial1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-mistral-trial1_v1
is_internal_developer: False
language_model: Trace2333/mistral_trial1
model_size: 13B
ranking_group: single
us_pacific_date: 2024-09-04
win_ratio: 0.5065700045310376
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name trace2333-mistral-trial1-v1-mkmlizer
Waiting for job on trace2333-mistral-trial1-v1-mkmlizer to finish
trace2333-mistral-trial1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial1-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial1-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial1-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial1-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial1-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial1-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial1-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial1-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-trial1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial1-v1-mkmlizer: Downloaded to shared memory in 64.715s
trace2333-mistral-trial1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1_zpgz2x, device:0
trace2333-mistral-trial1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial1-v1-mkmlizer: quantized model in 35.374s
trace2333-mistral-trial1-v1-mkmlizer: Processed model Trace2333/mistral_trial1 in 100.089s
trace2333-mistral-trial1-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial1-v1
trace2333-mistral-trial1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial1-v1/config.json
trace2333-mistral-trial1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial1-v1/special_tokens_map.json
trace2333-mistral-trial1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trial1-v1/tokenizer_config.json
trace2333-mistral-trial1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial1-v1/tokenizer.json
trace2333-mistral-trial1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial1-v1/flywheel_model.0.safetensors
trace2333-mistral-trial1-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 52.42it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:04, 76.93it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 87.12it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 88.01it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:03, 87.54it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 84.84it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:13, 21.65it/s]
Loading 0:  22%|██▏       | 79/363 [00:01<00:09, 30.02it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 38.24it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 44.08it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 58.26it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:03, 63.75it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:03, 65.25it/s]
Loading 0:  38%|███▊      | 139/363 [00:02<00:03, 68.55it/s]
Loading 0:  41%|████      | 148/363 [00:03<00:09, 21.86it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:07, 27.97it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:05, 34.84it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 43.85it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 51.45it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:02, 60.06it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:02, 65.56it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:01, 75.28it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:05, 24.20it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:04, 29.53it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:03, 36.06it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 44.94it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 57.82it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 63.17it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 68.29it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 24.46it/s]
Loading 0:  86%|████████▌ | 313/363 [00:07<00:01, 29.94it/s]
Loading 0:  89%|████████▉ | 323/363 [00:07<00:01, 37.60it/s]
Loading 0:  93%|█████████▎| 337/363 [00:07<00:00, 49.07it/s]
Loading 0:  96%|█████████▌| 347/363 [00:07<00:00, 56.57it/s]
Loading 0:  98%|█████████▊| 356/363 [00:08<00:00, 61.62it/s]
                                                            
Job trace2333-mistral-trial1-v1-mkmlizer completed after 125.39s with status: succeeded
Stopping job with name trace2333-mistral-trial1-v1-mkmlizer
Pipeline stage MKMLizer completed in 126.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial1-v1
Waiting for inference service trace2333-mistral-trial1-v1 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
Inference service trace2333-mistral-trial1-v1 ready after 130.61964559555054s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.536973476409912s
Received healthy response to inference request in 1.8331632614135742s
Received healthy response to inference request in 1.8537139892578125s
Received healthy response to inference request in 2.2718722820281982s
Received healthy response to inference request in 2.4116437435150146s
5 requests
0 failed requests
5th percentile: 1.837273406982422
10th percentile: 1.8413835525512696
20th percentile: 1.8496038436889648
30th percentile: 1.9373456478118896
40th percentile: 2.104608964920044
50th percentile: 2.2718722820281982
60th percentile: 2.3277808666229247
70th percentile: 2.383689451217651
80th percentile: 2.436709690093994
90th percentile: 2.486841583251953
95th percentile: 2.511907529830933
99th percentile: 2.5319602870941162
mean time: 2.1814733505249024
Pipeline stage StressChecker completed in 11.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.20s
trace2333-mistral-trial1_v1 status is now deployed due to DeploymentManager action
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 trace2333-mistral-trial1-v1-profiler
Waiting for inference service trace2333-mistral-trial1-v1-profiler to be ready
Inference service trace2333-mistral-trial1-v1-profiler ready after 150.56288242340088s
Pipeline stage MKMLProfilerDeployer completed in 150.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial1-v1-profiler-predictor-00001-deplolpw9t:/code/chaiverse_profiler_1725471920 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial1-v1-profiler-predictor-00001-deplolpw9t --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725471920 && 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_1725471920/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial1-v1-profiler is running
Tearing down inference service trace2333-mistral-trial1-v1-profiler
Service trace2333-mistral-trial1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.58s
Shutdown handler unregistered and original handlers restored
trace2333-mistral-trial1_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trial1_v1 status is now torndown due to DeploymentManager action