trace2333-mistral-trail8

submission_id: trace2333-mistral-trail8_v3

developer_uid: Trace2333

alignment_samples: 12281

alignment_score: -0.29918438189542435

best_of: 8

celo_rating: 1247.94

display_name: trace2333-mistral-trail8_v3

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_trail8

latencies: [{'batch_size': 1, 'throughput': 0.7023742801035765, 'latency_mean': 1.423635848760605, 'latency_p50': 1.4126954078674316, 'latency_p90': 1.6009939193725586}, {'batch_size': 3, 'throughput': 1.3361928144494415, 'latency_mean': 2.239290415048599, 'latency_p50': 2.248861074447632, 'latency_p90': 2.467824530601501}, {'batch_size': 5, 'throughput': 1.5792376699878927, 'latency_mean': 3.1523211467266083, 'latency_p50': 3.1584348678588867, 'latency_p90': 3.573955011367798}, {'batch_size': 6, 'throughput': 1.6264027953084557, 'latency_mean': 3.6803011977672577, 'latency_p50': 3.672764301300049, 'latency_p90': 4.209412932395935}, {'batch_size': 8, 'throughput': 1.6189210439782438, 'latency_mean': 4.921230162382126, 'latency_p50': 4.987264633178711, 'latency_p90': 5.587256574630738}, {'batch_size': 10, 'throughput': 1.5487846148374018, 'latency_mean': 6.422537294626236, 'latency_p50': 6.472227215766907, 'latency_p90': 7.228198766708374}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Trace2333/mistral_trail8

model_name: trace2333-mistral-trail8_v3

model_num_parameters: 12772070400.0

model_repo: Trace2333/mistral_trail8

model_size: 13B

num_battles: 12279

num_wins: 6310

propriety_score: 0.7579908675799086

propriety_total_count: 1095.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.63

timestamp: 2024-09-10T12:02:00+00:00

us_pacific_date: 2024-09-10

win_ratio: 0.5138854955615278

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-trail8-v3-mkmlizer
Waiting for job on trace2333-mistral-trail8-v3-mkmlizer to finish
trace2333-mistral-trail8-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trail8-v3-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-trail8-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-trail8-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-trail8-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-trail8-v3-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-trail8-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-trail8-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-trail8-v3-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-trail8-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-trail8-v3-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-trail8-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v3-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-trail8-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-trail8-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-trail8-v3-mkmlizer: ║                                                                     ║
trace2333-mistral-trail8-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:58358->127.0.0.1:8080: write tcp 127.0.0.1:58358->127.0.0.1:8080: use of closed network connection\n')
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
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
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
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
trace2333-mistral-trail8-v3-mkmlizer: Downloaded to shared memory in 29.097s
trace2333-mistral-trail8-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzrcobuyy, device:0
trace2333-mistral-trail8-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-trail8-v3-mkmlizer: quantized model in 36.694s
trace2333-mistral-trail8-v3-mkmlizer: Processed model Trace2333/mistral_trail8 in 65.792s
trace2333-mistral-trail8-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trail8-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trail8-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trail8-v3
trace2333-mistral-trail8-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v3/config.json
trace2333-mistral-trail8-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v3/special_tokens_map.json
trace2333-mistral-trail8-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v3/tokenizer_config.json
trace2333-mistral-trail8-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trail8-v3/tokenizer.json
trace2333-mistral-trail8-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trail8-v3/flywheel_model.0.safetensors
trace2333-mistral-trail8-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 47.45it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 60.29it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 69.03it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 74.53it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 76.63it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 70.45it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:16, 18.66it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.78it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 30.53it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 36.67it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 44.20it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 51.52it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 56.75it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 62.66it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 67.58it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 19.81it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.74it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.62it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 37.49it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 44.12it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 51.67it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 57.05it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 60.00it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 65.47it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:07, 19.93it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:05, 25.88it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.77it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 40.07it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 45.60it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 52.75it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 59.74it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 65.56it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 63.94it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 19.99it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 26.89it/s]
Loading 0:  89%|████████▊ | 322/363 [00:08<00:01, 32.34it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.77it/s]
Loading 0:  94%|█████████▎| 340/363 [00:08<00:00, 46.05it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 52.95it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 56.61it/s]
                                                            
Job trace2333-mistral-trail8-v3-mkmlizer completed after 94.3s with status: succeeded
Stopping job with name trace2333-mistral-trail8-v3-mkmlizer
Pipeline stage MKMLizer completed in 96.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-trail8-v3
Waiting for inference service trace2333-mistral-trail8-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service trace2333-mistral-trail8-v3 ready after 150.45097875595093s
Pipeline stage MKMLDeployer completed in 151.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6199870109558105s
Received healthy response to inference request in 2.0475473403930664s
Received healthy response to inference request in 1.6641311645507812s
Received healthy response to inference request in 1.6916723251342773s
Received healthy response to inference request in 2.2136194705963135s
5 requests
0 failed requests
5th percentile: 1.6696393966674805
10th percentile: 1.6751476287841798
20th percentile: 1.686164093017578
30th percentile: 1.762847328186035
40th percentile: 1.9051973342895507
50th percentile: 2.0475473403930664
60th percentile: 2.1139761924743654
70th percentile: 2.180405044555664
80th percentile: 2.294892978668213
90th percentile: 2.457439994812012
95th percentile: 2.538713502883911
99th percentile: 2.6037323093414306
mean time: 2.0473914623260496
Pipeline stage StressChecker completed in 12.79s
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 4.99s
Shutdown handler de-registered
trace2333-mistral-trail8_v3 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-trail8-v3-profiler
Waiting for inference service trace2333-mistral-trail8-v3-profiler to be ready
Inference service trace2333-mistral-trail8-v3-profiler ready after 160.37418866157532s
Pipeline stage MKMLProfilerDeployer completed in 160.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trail8-v3-profiler-predictor-00001-deploqg8bx:/code/chaiverse_profiler_1725970188 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trail8-v3-profiler-predictor-00001-deploqg8bx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725970188 && 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_1725970188/summary.json'
kubectl exec -it trace2333-mistral-trail8-v3-profiler-predictor-00001-deploqg8bx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725970188/summary.json'
Pipeline stage MKMLProfilerRunner completed in 942.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trail8-v3-profiler is running
Tearing down inference service trace2333-mistral-trail8-v3-profiler
Service trace2333-mistral-trail8-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.97s
Shutdown handler de-registered
trace2333-mistral-trail8_v3 status is now inactive due to auto deactivation removed underperforming models