submission_id: trace2333-mistral-trial6_v5
developer_uid: Trace2333
alignment_samples: 11026
alignment_score: -0.012248537185910208
best_of: 8
celo_rating: 1258.91
display_name: trace2333-mistral-trial6_v5
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': 0.6892656079808674, 'latency_mean': 1.4507310903072357, 'latency_p50': 1.4403878450393677, 'latency_p90': 1.6189053535461426}, {'batch_size': 3, 'throughput': 1.312185032035087, 'latency_mean': 2.282902193069458, 'latency_p50': 2.2937402725219727, 'latency_p90': 2.532645082473755}, {'batch_size': 5, 'throughput': 1.524739921315781, 'latency_mean': 3.2693074214458466, 'latency_p50': 3.2678250074386597, 'latency_p90': 3.643530988693237}, {'batch_size': 6, 'throughput': 1.593144520647626, 'latency_mean': 3.742696541547775, 'latency_p50': 3.791711688041687, 'latency_p90': 4.207233095169067}, {'batch_size': 8, 'throughput': 1.5705198528649378, 'latency_mean': 5.054116045236587, 'latency_p50': 5.0595327615737915, 'latency_p90': 5.66349048614502}, {'batch_size': 10, 'throughput': 1.5198037306687295, 'latency_mean': 6.529887545108795, 'latency_p50': 6.531020283699036, 'latency_p90': 7.534984397888183}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial6
model_name: trace2333-mistral-trial6_v5
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial6
model_size: 13B
num_battles: 11025
num_wins: 5759
propriety_score: 0.7511961722488039
propriety_total_count: 1045.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.6
timestamp: 2024-09-06T17:30:47+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5223582766439909
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-v5-mkmlizer
Waiting for job on trace2333-mistral-trial6-v5-mkmlizer to finish
trace2333-mistral-trial6-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v5-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trial6-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trial6-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trial6-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trial6-v5-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trial6-v5-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trial6-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trial6-v5-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trial6-v5-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trial6-v5-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trial6-v5-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v5-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trial6-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trial6-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trial6-v5-mkmlizer: ║                                                                     ║
trace2333-mistral-trial6-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial6-v5-mkmlizer: Downloaded to shared memory in 28.002s
trace2333-mistral-trial6-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe_ykfaih, device:0
trace2333-mistral-trial6-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trial6-v5-mkmlizer: quantized model in 36.613s
trace2333-mistral-trial6-v5-mkmlizer: Processed model Trace2333/mistral_trial6 in 64.615s
trace2333-mistral-trial6-v5-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v5
trace2333-mistral-trial6-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v5/config.json
trace2333-mistral-trial6-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v5/tokenizer.json
trace2333-mistral-trial6-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v5/flywheel_model.0.safetensors
trace2333-mistral-trial6-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.79it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 82.96it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:03, 92.76it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 74.35it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 73.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:15, 19.76it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:11, 25.46it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 32.18it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 38.18it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 45.01it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 49.83it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:04, 61.43it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:03, 66.51it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:03, 65.92it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:11, 19.19it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 24.23it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 29.99it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 36.46it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 43.98it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 48.94it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 55.58it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 61.38it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 66.98it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:07, 19.85it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.73it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 40.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 47.55it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 52.97it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 57.12it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 61.53it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 65.38it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 20.10it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 23.42it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 29.34it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:00, 36.74it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 43.94it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 50.82it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 54.67it/s]
Loading 0: 100%|██████████| 363/363 [00:15<00:00,  4.24it/s]
                                                            

Job trace2333-mistral-trial6-v5-mkmlizer completed after 94.49s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v5-mkmlizer
Pipeline stage MKMLizer completed in 96.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trial6-v5
Waiting for inference service trace2333-mistral-trial6-v5 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
Failed to get response for submission blend_jitik_2024-08-26: ('http://mistralai-mixtral-8x7b-3473-v131-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\')]"}')
Inference service trace2333-mistral-trial6-v5 ready after 151.24300861358643s
Pipeline stage MKMLDeployer completed in 151.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4707298278808594s
Received healthy response to inference request in 2.1246912479400635s
Received healthy response to inference request in 1.859590768814087s
Received healthy response to inference request in 1.769129753112793s
Received healthy response to inference request in 1.7440853118896484s
5 requests
0 failed requests
5th percentile: 1.7490942001342773
10th percentile: 1.7541030883789062
20th percentile: 1.764120864868164
30th percentile: 1.7872219562530518
40th percentile: 1.8234063625335692
50th percentile: 1.859590768814087
60th percentile: 1.9656309604644775
70th percentile: 2.071671152114868
80th percentile: 2.193898963928223
90th percentile: 2.332314395904541
95th percentile: 2.4015221118927
99th percentile: 2.4568882846832274
mean time: 1.9936453819274902
Pipeline stage StressChecker completed in 10.79s
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 6.10s
Shutdown handler de-registered
trace2333-mistral-trial6_v5 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 trace2333-mistral-trial6-v5-profiler
Waiting for inference service trace2333-mistral-trial6-v5-profiler to be ready
Inference service trace2333-mistral-trial6-v5-profiler ready after 140.32801365852356s
Pipeline stage MKMLProfilerDeployer completed in 140.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial6-v5-profiler-predictor-00001-deploczl8k:/code/chaiverse_profiler_1725644290 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial6-v5-profiler-predictor-00001-deploczl8k --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725644290 && 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_1725644290/summary.json'
kubectl exec -it trace2333-mistral-trial6-v5-profiler-predictor-00001-deploczl8k --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725644290/summary.json'
Pipeline stage MKMLProfilerRunner completed in 963.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v5-profiler is running
Tearing down inference service trace2333-mistral-trial6-v5-profiler
Service trace2333-mistral-trial6-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.69s
Shutdown handler de-registered
trace2333-mistral-trial6_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics