submission_id: trace2333-mistral-trial6_v9
developer_uid: Trace2333
best_of: 8
celo_rating: 1252.62
display_name: trace2333-mistral-trial6_v9
family_friendly_score: 0.0
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': 0.6950996167593139, 'latency_mean': 1.438545718193054, 'latency_p50': 1.4273693561553955, 'latency_p90': 1.6027210712432862}, {'batch_size': 3, 'throughput': 1.3305475134350775, 'latency_mean': 2.248687745332718, 'latency_p50': 2.226837992668152, 'latency_p90': 2.494671869277954}, {'batch_size': 5, 'throughput': 1.5753271559419646, 'latency_mean': 3.152084484100342, 'latency_p50': 3.1452490091323853, 'latency_p90': 3.560555768013}, {'batch_size': 6, 'throughput': 1.6146969706690284, 'latency_mean': 3.681075146198273, 'latency_p50': 3.6742465496063232, 'latency_p90': 4.157620072364807}, {'batch_size': 8, 'throughput': 1.6114963609668644, 'latency_mean': 4.921248828172684, 'latency_p50': 4.940051555633545, 'latency_p90': 5.538960790634155}, {'batch_size': 10, 'throughput': 1.5510680409592956, 'latency_mean': 6.416942157745361, 'latency_p50': 6.447903037071228, 'latency_p90': 7.378565239906311}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_trial6
model_name: trace2333-mistral-trial6_v9
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_trial6
model_size: 13B
num_battles: 12682
num_wins: 6874
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.63
timestamp: 2024-09-07T04:16:33+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5420280712821322
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-v9-mkmlizer
Waiting for job on trace2333-mistral-trial6-v9-mkmlizer to finish
trace2333-mistral-trial6-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-trial6-v9-mkmlizer: ║ _____ __ __ ║
trace2333-mistral-trial6-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-mistral-trial6-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-mistral-trial6-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-mistral-trial6-v9-mkmlizer: ║ /___/ ║
trace2333-mistral-trial6-v9-mkmlizer: ║ ║
trace2333-mistral-trial6-v9-mkmlizer: ║ Version: 0.10.1 ║
trace2333-mistral-trial6-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-mistral-trial6-v9-mkmlizer: ║ https://mk1.ai ║
trace2333-mistral-trial6-v9-mkmlizer: ║ ║
trace2333-mistral-trial6-v9-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-mistral-trial6-v9-mkmlizer: ║ belonging to: ║
trace2333-mistral-trial6-v9-mkmlizer: ║ ║
trace2333-mistral-trial6-v9-mkmlizer: ║ Chai Research Corp. ║
trace2333-mistral-trial6-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-mistral-trial6-v9-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-mistral-trial6-v9-mkmlizer: ║ ║
trace2333-mistral-trial6-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-trial6-v9-mkmlizer: Downloaded to shared memory in 55.325s
trace2333-mistral-trial6-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr33vvhbx, device:0
trace2333-mistral-trial6-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-trial6-v9-mkmlizer: quantized model in 36.591s
trace2333-mistral-trial6-v9-mkmlizer: Processed model Trace2333/mistral_trial6 in 91.916s
trace2333-mistral-trial6-v9-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-trial6-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-trial6-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-trial6-v9
trace2333-mistral-trial6-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v9/config.json
trace2333-mistral-trial6-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v9/special_tokens_map.json
trace2333-mistral-trial6-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v9/tokenizer_config.json
trace2333-mistral-trial6-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-trial6-v9/tokenizer.json
trace2333-mistral-trial6-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-trial6-v9/flywheel_model.0.safetensors
trace2333-mistral-trial6-v9-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:07, 47.17it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:06, 55.75it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:05, 63.03it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:04, 67.89it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 68.35it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:04, 67.22it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:15, 19.05it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 24.47it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 30.34it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 36.70it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 41.69it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 48.45it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 54.59it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:04, 59.12it/s] Loading 0: 37%|███▋ | 133/363 [00:03<00:03, 61.17it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:11, 19.92it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 25.66it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.16it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 38.72it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 43.94it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 50.60it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:03, 53.84it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:02, 58.71it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:02, 57.95it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:07, 19.61it/s] Loading 0: 64%|██████▍ | 232/363 [00:06<00:05, 24.87it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 31.04it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:03, 36.43it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 42.49it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:01, 48.63it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:01, 54.26it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:01, 58.64it/s] Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 60.91it/s] Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 20.12it/s] Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 25.73it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 32.16it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 39.06it/s] Loading 0: 94%|█████████▎| 340/363 [00:09<00:00, 45.81it/s] Loading 0: 96%|█████████▌| 349/363 [00:09<00:00, 50.40it/s] Loading 0: 99%|█████████▊| 358/363 [00:09<00:00, 55.95it/s]
Job trace2333-mistral-trial6-v9-mkmlizer completed after 115.26s with status: succeeded
Stopping job with name trace2333-mistral-trial6-v9-mkmlizer
Pipeline stage MKMLizer completed in 117.03s
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-v9
Waiting for inference service trace2333-mistral-trial6-v9 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
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
Inference service trace2333-mistral-trial6-v9 ready after 240.78208708763123s
Pipeline stage MKMLDeployer completed in 241.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1790974140167236s
Received healthy response to inference request in 2.0098214149475098s
Received healthy response to inference request in 2.0131630897521973s
Received healthy response to inference request in 2.3251864910125732s
Received healthy response to inference request in 2.0652363300323486s
5 requests
0 failed requests
5th percentile: 2.010489749908447
10th percentile: 2.011158084869385
20th percentile: 2.01249475479126
30th percentile: 2.0235777378082274
40th percentile: 2.044407033920288
50th percentile: 2.0652363300323486
60th percentile: 2.1107807636260985
70th percentile: 2.1563251972198487
80th percentile: 2.2083152294158936
90th percentile: 2.266750860214233
95th percentile: 2.2959686756134032
99th percentile: 2.3193429279327393
mean time: 2.1185009479522705
Pipeline stage StressChecker completed in 11.41s
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 4.45s
Shutdown handler de-registered
trace2333-mistral-trial6_v9 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 0.13s
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-v9-profiler
Waiting for inference service trace2333-mistral-trial6-v9-profiler to be ready
Inference service trace2333-mistral-trial6-v9-profiler ready after 130.2958550453186s
Pipeline stage MKMLProfilerDeployer completed in 130.64s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-trial6-v9-profiler-predictor-00001-deplocn5gp:/code/chaiverse_profiler_1725683133 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-trial6-v9-profiler-predictor-00001-deplocn5gp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725683133 && 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_1725683133/summary.json'
kubectl exec -it trace2333-mistral-trial6-v9-profiler-predictor-00001-deplocn5gp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725683133/summary.json'
Pipeline stage MKMLProfilerRunner completed in 947.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-trial6-v9-profiler is running
Tearing down inference service trace2333-mistral-trial6-v9-profiler
Service trace2333-mistral-trial6-v9-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.67s
Shutdown handler de-registered
trace2333-mistral-trial6_v9 status is now inactive due to auto deactivation removed underperforming models
trace2333-mistral-trial6_v9 status is now torndown due to DeploymentManager action