submission_id: trace2333-mistral-trial6_v6
developer_uid: Trace2333
alignment_samples: 11785
alignment_score: -0.04211023761645136
best_of: 8
celo_rating: 1255.66
display_name: trace2333-mistral-trial6_v6
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_trial6
latencies: [{'batch_size': 1, 'throughput': 0.6875350357843835, 'latency_mean': 1.454413765668869, 'latency_p50': 1.4501441717147827, 'latency_p90': 1.6236037731170654}, {'batch_size': 3, 'throughput': 1.3114133114324216, 'latency_mean': 2.284491777420044, 'latency_p50': 2.278613328933716, 'latency_p90': 2.5419103384017943}, {'batch_size': 5, 'throughput': 1.5497824812176024, 'latency_mean': 3.2122978937625883, 'latency_p50': 3.21246600151062, 'latency_p90': 3.665195345878601}, {'batch_size': 6, 'throughput': 1.5711260841527075, 'latency_mean': 3.7973102390766145, 'latency_p50': 3.8249716758728027, 'latency_p90': 4.186433100700379}, {'batch_size': 8, 'throughput': 1.5804647523188329, 'latency_mean': 5.029477062225342, 'latency_p50': 5.0435545444488525, 'latency_p90': 5.770536041259765}, {'batch_size': 10, 'throughput': 1.5320944449502047, 'latency_mean': 6.4814186131954195, 'latency_p50': 6.517668843269348, 'latency_p90': 7.28006739616394}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial6
model_name: trace2333-mistral-trial6_v6
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial6
model_size: 13B
num_battles: 11785
num_wins: 6111
propriety_score: 0.7492904446546831
propriety_total_count: 1057.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.58
timestamp: 2024-09-06T17:39:08+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5185405176071277
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-trial6-v6-mkmlizer
Waiting for job on trace2333-mistral-trial6-v6-mkmlizer to finish
trace2333-mistral-trial6-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v6-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial6-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial6-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial6-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial6-v6-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial6-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v6-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial6-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial6-v6-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial6-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial6-v6-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial6-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v6-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial6-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial6-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial6-v6-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial6-v6-mkmlizer: Downloaded to shared memory in 28.082s
trace2333-mistral-trial6-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuz3oqpbe, device:0
trace2333-mistral-trial6-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial6-v6-mkmlizer: quantized model in 36.271s
trace2333-mistral-trial6-v6-mkmlizer: Processed model Trace2333/mistral_trial6 in 64.353s
trace2333-mistral-trial6-v6-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v6
trace2333-mistral-trial6-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v6/config.json
trace2333-mistral-trial6-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v6/special_tokens_map.json
trace2333-mistral-trial6-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v6/tokenizer_config.json
trace2333-mistral-trial6-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v6/tokenizer.json
trace2333-mistral-trial6-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v6/flywheel_model.0.safetensors
trace2333-mistral-trial6-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.93it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:04, 70.53it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 76.01it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 86.39it/s]
Loading 0:  14%|█▍        | 51/363 [00:00<00:03, 93.49it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:13, 21.84it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 32.16it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.64it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 44.86it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 50.32it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 55.43it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:04, 57.79it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:03, 63.04it/s]
Loading 0:  38%|███▊      | 139/363 [00:02<00:03, 68.12it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:10, 20.88it/s]
Loading 0:  42%|████▏     | 153/363 [00:03<00:08, 23.76it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:07, 28.45it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 36.09it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 44.63it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 51.47it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 59.34it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 64.46it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 67.69it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:07, 19.80it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 24.75it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 31.21it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 38.66it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 44.50it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 50.82it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 57.82it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 62.00it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:01, 65.86it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.40it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 26.47it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 33.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.02it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 47.64it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 54.11it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 59.00it/s]
                                                            

Job trace2333-mistral-trial6-v6-mkmlizer completed after 85.39s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v6-mkmlizer
Pipeline stage MKMLizer completed in 86.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial6-v6
Waiting for inference service trace2333-mistral-trial6-v6 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-mistral-trial6-v6 ready after 140.990873336792s
Pipeline stage MKMLDeployer completed in 141.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.106717348098755s
Received healthy response to inference request in 1.8365929126739502s
Received healthy response to inference request in 2.4144396781921387s
Received healthy response to inference request in 1.4406208992004395s
Received healthy response to inference request in 2.82425856590271s
5 requests
0 failed requests
5th percentile: 1.5198153018951417
10th percentile: 1.5990097045898437
20th percentile: 1.757398509979248
30th percentile: 1.890617799758911
40th percentile: 1.998667573928833
50th percentile: 2.106717348098755
60th percentile: 2.2298062801361085
70th percentile: 2.3528952121734616
80th percentile: 2.496403455734253
90th percentile: 2.6603310108184814
95th percentile: 2.7422947883605957
99th percentile: 2.8078658103942873
mean time: 2.1245258808135987
Pipeline stage StressChecker completed in 11.64s
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 6.63s
Shutdown handler de-registered
trace2333-mistral-trial6_v6 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-trial6-v6-profiler
Waiting for inference service trace2333-mistral-trial6-v6-profiler to be ready
Inference service trace2333-mistral-trial6-v6-profiler ready after 150.3461401462555s
Pipeline stage MKMLProfilerDeployer completed in 151.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial6-v6-profiler-predictor-00001-deplo4kd7b:/code/chaiverse_profiler_1725644786 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial6-v6-profiler-predictor-00001-deplo4kd7b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725644786 && 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_1725644786/summary.json'
kubectl exec -it trace2333-mistral-trial6-v6-profiler-predictor-00001-deplo4kd7b --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725644786/summary.json'
Pipeline stage MKMLProfilerRunner completed in 964.04s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v6-profiler is running
Tearing down inference service trace2333-mistral-trial6-v6-profiler
Service trace2333-mistral-trial6-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.65s
Shutdown handler de-registered
trace2333-mistral-trial6_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics