submission_id: riverise-mistral-0920_v3
developer_uid: Riverise
best_of: 8
celo_rating: 1252.92
display_name: riverise-mistral-0920_v3
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': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 30, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Riverise/mistral_0920
latencies: [{'batch_size': 1, 'throughput': 0.6166913448463864, 'latency_mean': 1.6214919376373291, 'latency_p50': 1.6227867603302002, 'latency_p90': 1.773893117904663}, {'batch_size': 3, 'throughput': 1.0918109990618825, 'latency_mean': 2.7433987522125243, 'latency_p50': 2.737950921058655, 'latency_p90': 3.0424190521240235}, {'batch_size': 5, 'throughput': 1.232504072533467, 'latency_mean': 4.041522045135498, 'latency_p50': 4.045285701751709, 'latency_p90': 4.463338112831115}, {'batch_size': 6, 'throughput': 1.26916105742702, 'latency_mean': 4.709285593032837, 'latency_p50': 4.7595168352127075, 'latency_p90': 5.334226512908936}, {'batch_size': 8, 'throughput': 1.2494969679492343, 'latency_mean': 6.3805814504623415, 'latency_p50': 6.3929126262664795, 'latency_p90': 7.155306124687195}, {'batch_size': 10, 'throughput': 1.211690918900314, 'latency_mean': 8.202978187799454, 'latency_p50': 8.284517407417297, 'latency_p90': 9.320258641242981}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Riverise/mistral_0920
model_name: riverise-mistral-0920_v3
model_num_parameters: 12772070400.0
model_repo: Riverise/mistral_0920
model_size: 13B
num_battles: 369574
num_wins: 187348
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.21
timestamp: 2024-09-21T09:37:41+00:00
us_pacific_date: 2024-09-21
win_ratio: 0.5069296000259759
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 riverise-mistral-0920-v3-mkmlizer
Waiting for job on riverise-mistral-0920-v3-mkmlizer to finish
riverise-mistral-0920-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-mistral-0920-v3-mkmlizer: ║ _____ __ __ ║
riverise-mistral-0920-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
riverise-mistral-0920-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
riverise-mistral-0920-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
riverise-mistral-0920-v3-mkmlizer: ║ /___/ ║
riverise-mistral-0920-v3-mkmlizer: ║ ║
riverise-mistral-0920-v3-mkmlizer: ║ Version: 0.10.1 ║
riverise-mistral-0920-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
riverise-mistral-0920-v3-mkmlizer: ║ https://mk1.ai ║
riverise-mistral-0920-v3-mkmlizer: ║ ║
riverise-mistral-0920-v3-mkmlizer: ║ The license key for the current software has been verified as ║
riverise-mistral-0920-v3-mkmlizer: ║ belonging to: ║
riverise-mistral-0920-v3-mkmlizer: ║ ║
riverise-mistral-0920-v3-mkmlizer: ║ Chai Research Corp. ║
riverise-mistral-0920-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
riverise-mistral-0920-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
riverise-mistral-0920-v3-mkmlizer: ║ ║
riverise-mistral-0920-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-small_5341_v11: ('http://mistralai-mistral-small-5341-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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
riverise-mistral-0920-v3-mkmlizer: Downloaded to shared memory in 48.992s
riverise-mistral-0920-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg_mt7msy, device:0
riverise-mistral-0920-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-mistral-0920-v3-mkmlizer: quantized model in 37.201s
riverise-mistral-0920-v3-mkmlizer: Processed model Riverise/mistral_0920 in 86.193s
riverise-mistral-0920-v3-mkmlizer: creating bucket guanaco-mkml-models
riverise-mistral-0920-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-mistral-0920-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-mistral-0920-v3
riverise-mistral-0920-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-mistral-0920-v3/special_tokens_map.json
riverise-mistral-0920-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-mistral-0920-v3/config.json
riverise-mistral-0920-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-mistral-0920-v3/tokenizer_config.json
riverise-mistral-0920-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-mistral-0920-v3/tokenizer.json
Failed to get response for submission mistralai-mistral-small_5341_v11: ('http://mistralai-mistral-small-5341-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
riverise-mistral-0920-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-mistral-0920-v3/flywheel_model.0.safetensors
riverise-mistral-0920-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:07, 46.71it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:05, 63.16it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:04, 69.80it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:04, 70.74it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 69.96it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:04, 68.06it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:16, 18.39it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 24.32it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 30.65it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 35.91it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 42.72it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 49.74it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 53.61it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:04, 56.74it/s] Loading 0: 37%|███▋ | 133/363 [00:03<00:03, 60.45it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:11, 19.82it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 25.59it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 31.48it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 38.12it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 44.42it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 50.23it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:03, 55.25it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:02, 59.47it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:02, 62.57it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:07, 19.11it/s] Loading 0: 64%|██████▍ | 232/363 [00:06<00:05, 24.61it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 31.45it/s] Loading 0: 69%|██████▉ | 251/363 [00:06<00:02, 40.29it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 45.75it/s] Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 49.81it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:01, 52.87it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:01, 57.90it/s] Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 62.54it/s] Loading 0: 84%|████████▎ | 304/363 [00:08<00:03, 19.46it/s] Loading 0: 86%|████████▌ | 313/363 [00:08<00:02, 24.87it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 31.52it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 38.41it/s] Loading 0: 94%|█████████▎| 340/363 [00:09<00:00, 44.10it/s] Loading 0: 96%|█████████▌| 349/363 [00:09<00:00, 49.15it/s] Loading 0: 99%|█████████▊| 358/363 [00:09<00:00, 55.68it/s]
Job riverise-mistral-0920-v3-mkmlizer completed after 114.96s with status: succeeded
Stopping job with name riverise-mistral-0920-v3-mkmlizer
Pipeline stage MKMLizer completed in 115.76s
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 riverise-mistral-0920-v3
Waiting for inference service riverise-mistral-0920-v3 to be ready
Failed to get response for submission mistralai-mistral-small_5341_v11: ('http://mistralai-mistral-small-5341-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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
Failed to get response for submission function_sabet_2024-09-10: ('http://zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41580->127.0.0.1:8080: read: connection reset by peer\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
Inference service riverise-mistral-0920-v3 ready after 200.59945440292358s
Pipeline stage MKMLDeployer completed in 202.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.594782590866089s
Received healthy response to inference request in 6.38529109954834s
Received healthy response to inference request in 2.4773550033569336s
Received healthy response to inference request in 1.834538459777832s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 3.3108770847320557s
5 requests
0 failed requests
5th percentile: 1.9631017684936523
10th percentile: 2.0916650772094725
20th percentile: 2.3487916946411134
30th percentile: 2.5008405208587647
40th percentile: 2.5478115558624266
50th percentile: 2.594782590866089
60th percentile: 2.8812203884124754
70th percentile: 3.167658185958862
80th percentile: 3.925759887695313
90th percentile: 5.155525493621827
95th percentile: 5.7704082965850825
99th percentile: 6.262314538955688
mean time: 3.32056884765625
Pipeline stage StressChecker completed in 27.35s
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 8.60s
Shutdown handler de-registered
riverise-mistral-0920_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 0.13s
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 riverise-mistral-0920-v3-profiler
Waiting for inference service riverise-mistral-0920-v3-profiler to be ready
Inference service riverise-mistral-0920-v3-profiler ready after 190.43591856956482s
Pipeline stage MKMLProfilerDeployer completed in 193.21s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/riverise-mistral-0920-v3-profiler-predictor-00001-deploymejhp86:/code/chaiverse_profiler_1726912057 --namespace tenant-chaiml-guanaco
kubectl exec -it riverise-mistral-0920-v3-profiler-predictor-00001-deploymejhp86 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726912057 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726912057/summary.json'
kubectl exec -it riverise-mistral-0920-v3-profiler-predictor-00001-deploymejhp86 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726912057/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1171.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-mistral-0920-v3-profiler is running
Tearing down inference service riverise-mistral-0920-v3-profiler
Service riverise-mistral-0920-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.57s
Shutdown handler de-registered
riverise-mistral-0920_v3 status is now inactive due to auto deactivation removed underperforming models
riverise-mistral-0920_v3 status is now torndown due to DeploymentManager action