submission_id: trace2333-mistral-align-_8132_v2
developer_uid: Trace2333
alignment_samples: 12067
alignment_score: -0.24103104310224938
best_of: 8
celo_rating: 1253.29
display_name: trace2333-mistral-align-_8132_v2
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_1448
latencies: [{'batch_size': 1, 'throughput': 0.6902939462628194, 'latency_mean': 1.4485819089412688, 'latency_p50': 1.4577441215515137, 'latency_p90': 1.6267080545425414}, {'batch_size': 3, 'throughput': 1.3097950513864776, 'latency_mean': 2.2769064569473265, 'latency_p50': 2.271108388900757, 'latency_p90': 2.532657527923584}, {'batch_size': 5, 'throughput': 1.5469406366255272, 'latency_mean': 3.2199755299091337, 'latency_p50': 3.208256959915161, 'latency_p90': 3.608687090873718}, {'batch_size': 6, 'throughput': 1.6098313820586516, 'latency_mean': 3.7029591643810273, 'latency_p50': 3.70421040058136, 'latency_p90': 4.199087810516358}, {'batch_size': 8, 'throughput': 1.5783145366240787, 'latency_mean': 5.040529559850693, 'latency_p50': 5.085481524467468, 'latency_p90': 5.725123071670533}, {'batch_size': 10, 'throughput': 1.536543472537715, 'latency_mean': 6.457327079772949, 'latency_p50': 6.479593276977539, 'latency_p90': 7.336097407341003}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_align_
model_name: trace2333-mistral-align-_8132_v2
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_align_namo_1448
model_size: 13B
num_battles: 12067
num_wins: 6220
propriety_score: 0.76171875
propriety_total_count: 1024.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.62
timestamp: 2024-09-06T16:27:06+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5154553741609348
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-align-8132-v2-mkmlizer
Waiting for job on trace2333-mistral-align-8132-v2-mkmlizer to finish
trace2333-mistral-align-8132-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-align-8132-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-align-8132-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-align-8132-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-align-8132-v2-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-align-8132-v2-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-align-8132-v2-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-align-8132-v2-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-align-8132-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-align-8132-v2-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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 zonemercy-lexical-nemo-_1518_v27: ('http://zonemercy-lexical-nemo-1518-v27-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\')]"}')
trace2333-mistral-align-8132-v2-mkmlizer: Downloaded to shared memory in 34.693s
trace2333-mistral-align-8132-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxw3g_sa3, device:0
trace2333-mistral-align-8132-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-align-8132-v2-mkmlizer: quantized model in 35.372s
trace2333-mistral-align-8132-v2-mkmlizer: Processed model Trace2333/mistral_align_namo_1448 in 70.066s
trace2333-mistral-align-8132-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-align-8132-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-align-8132-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-align-8132-v2
trace2333-mistral-align-8132-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v2/config.json
trace2333-mistral-align-8132-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v2/special_tokens_map.json
trace2333-mistral-align-8132-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v2/tokenizer_config.json
trace2333-mistral-align-8132-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v2/tokenizer.json
trace2333-mistral-align-8132-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 52.83it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:03, 85.30it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 86.83it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:03, 84.78it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:03, 79.08it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 77.21it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:14, 20.59it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:12, 23.74it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:08, 34.73it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.44it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:05, 47.89it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 54.47it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:03, 61.11it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:03, 65.92it/s]
Loading 0:  38%|███▊      | 139/363 [00:02<00:03, 67.78it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:10, 21.25it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:07, 27.81it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 34.57it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 40.65it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 47.40it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:02, 55.94it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 59.58it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 65.12it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:06, 21.47it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:04, 27.59it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.14it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 43.19it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:01, 55.42it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 60.81it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 63.96it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:00, 69.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 23.29it/s]
Loading 0:  86%|████████▌ | 313/363 [00:07<00:01, 29.20it/s]
Loading 0:  89%|████████▊ | 322/363 [00:07<00:01, 34.30it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 40.61it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 54.33it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 61.67it/s]
                                                            

Job trace2333-mistral-align-8132-v2-mkmlizer completed after 96.01s with status: succeeded
Stopping job with name trace2333-mistral-align-8132-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-align-8132-v2
Waiting for inference service trace2333-mistral-align-8132-v2 to be ready
Failed to get response for submission zonemercy-base-story-v1_v7: ('http://zonemercy-base-story-v1-v7-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\')]"}')
Failed to get response for submission zonemercy-base-story-v1_v7: ('http://zonemercy-base-story-v1-v7-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\')]"}')
Failed to get response for submission zonemercy-lexical-nemo-_1518_v27: ('http://zonemercy-lexical-nemo-1518-v27-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\')]"}')
Failed to get response for submission zonemercy-base-story-v1_v7: ('http://zonemercy-base-story-v1-v7-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-align-8132-v2 ready after 150.80039954185486s
Pipeline stage MKMLDeployer completed in 151.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.050307035446167s
Received healthy response to inference request in 2.333918571472168s
Received healthy response to inference request in 1.9447860717773438s
Received healthy response to inference request in 2.1318650245666504s
Received healthy response to inference request in 1.7350835800170898s
5 requests
0 failed requests
5th percentile: 1.7770240783691407
10th percentile: 1.8189645767211915
20th percentile: 1.902845573425293
30th percentile: 1.9822018623352051
40th percentile: 2.0570334434509276
50th percentile: 2.1318650245666504
60th percentile: 2.2126864433288573
70th percentile: 2.2935078620910643
80th percentile: 2.477196264266968
90th percentile: 2.7637516498565673
95th percentile: 2.907029342651367
99th percentile: 3.021651496887207
mean time: 2.2391920566558836
Pipeline stage StressChecker completed in 12.11s
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 6.11s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v2 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-align-8132-v2-profiler
Waiting for inference service trace2333-mistral-align-8132-v2-profiler to be ready
Inference service trace2333-mistral-align-8132-v2-profiler ready after 150.35368466377258s
Pipeline stage MKMLProfilerDeployer completed in 150.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-al050aabb50de0632343653f5eca6bd9b6-deplo522pm:/code/chaiverse_profiler_1725640491 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-al050aabb50de0632343653f5eca6bd9b6-deplo522pm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725640491 && 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_1725640491/summary.json'
kubectl exec -it trace2333-mistral-al050aabb50de0632343653f5eca6bd9b6-deplo522pm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725640491/summary.json'
Pipeline stage MKMLProfilerRunner completed in 959.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-align-8132-v2-profiler is running
Tearing down inference service trace2333-mistral-align-8132-v2-profiler
Service trace2333-mistral-align-8132-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.78s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics