developer_uid: azuruce
submission_id: chaiml-0918-horror-retor_3693_v3
model_name: 0918_horror_retort_comp
model_group: ChaiML/0918_horror_retor
status: torndown
timestamp: 2024-09-19T19:28:44+00:00
num_battles: 13780
num_wins: 6719
celo_rating: 1245.71
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/0918_horror_retort_albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.633245627495992, 'latency_mean': 1.5791006219387054, 'latency_p50': 1.5758543014526367, 'latency_p90': 1.7438472747802733}, {'batch_size': 3, 'throughput': 1.2328028730055136, 'latency_mean': 2.4237471401691435, 'latency_p50': 2.4463096857070923, 'latency_p90': 2.636340308189392}, {'batch_size': 5, 'throughput': 1.5302334854680384, 'latency_mean': 3.250326702594757, 'latency_p50': 3.2481963634490967, 'latency_p90': 3.5904868125915526}, {'batch_size': 6, 'throughput': 1.632991414426275, 'latency_mean': 3.6568930447101593, 'latency_p50': 3.666616678237915, 'latency_p90': 4.12248957157135}, {'batch_size': 8, 'throughput': 1.7532980489073544, 'latency_mean': 4.5387620508670805, 'latency_p50': 4.581855535507202, 'latency_p90': 5.186317181587219}, {'batch_size': 10, 'throughput': 1.7810328353831197, 'latency_mean': 5.574332773685455, 'latency_p50': 5.576804041862488, 'latency_p90': 6.445503044128418}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 0918_horror_retort_comp
is_internal_developer: True
language_model: ChaiML/0918_horror_retort_albert
model_size: 13B
ranking_group: single
throughput_3p7s: 1.65
us_pacific_date: 2024-09-19
win_ratio: 0.4875907111756168
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n##Try to make the conversation scary while stay in character##\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}
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 chaiml-0918-horror-retor-3693-v3-mkmlizer
Waiting for job on chaiml-0918-horror-retor-3693-v3-mkmlizer to finish
chaiml-0918-horror-retor-3693-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ _____ __ __ ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ /___/ ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ Version: 0.10.1 ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ belonging to: ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-0918-horror-retor-3693-v3-mkmlizer: ║ ║
chaiml-0918-horror-retor-3693-v3-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission chaiml-chaiml-sft-horror_v2: ('http://chaiml-chaiml-sft-horror-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:53730->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-0918-horror-retor-3693-v3-mkmlizer: Downloaded to shared memory in 111.734s
chaiml-0918-horror-retor-3693-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdjrd_sq5, device:0
chaiml-0918-horror-retor-3693-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0918-horror-retor-3693-v3-mkmlizer: quantized model in 41.349s
chaiml-0918-horror-retor-3693-v3-mkmlizer: Processed model ChaiML/0918_horror_retort_albert in 153.084s
chaiml-0918-horror-retor-3693-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0918-horror-retor-3693-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0918-horror-retor-3693-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v3
chaiml-0918-horror-retor-3693-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v3/config.json
chaiml-0918-horror-retor-3693-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v3/special_tokens_map.json
chaiml-0918-horror-retor-3693-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v3/tokenizer_config.json
chaiml-0918-horror-retor-3693-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v3/tokenizer.json
chaiml-0918-horror-retor-3693-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v3/flywheel_model.0.safetensors
chaiml-0918-horror-retor-3693-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 23.38it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:11, 29.48it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.87it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 36.16it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:14, 23.58it/s] Loading 0: 8%|▊ | 29/363 [00:01<00:12, 25.70it/s] Loading 0: 9%|▉ | 33/363 [00:01<00:13, 23.79it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 28.87it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 27.67it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 29.63it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 27.91it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 28.10it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:09, 30.42it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:15, 19.50it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:11, 25.81it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 26.27it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 26.55it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 29.64it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 27.88it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 30.59it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 28.62it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 23.50it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:12, 21.15it/s] Loading 0: 30%|███ | 109/363 [00:04<00:09, 25.67it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.26it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 26.32it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 30.33it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 28.99it/s] Loading 0: 35%|███▌ | 128/363 [00:04<00:07, 31.14it/s] Loading 0: 36%|███▋ | 132/363 [00:04<00:08, 26.80it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.86it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 26.63it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:08, 24.83it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 23.32it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:06, 29.74it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 28.69it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 31.13it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 29.04it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 31.36it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.82it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 23.75it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 20.99it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:06, 28.24it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:05, 27.91it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.98it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 29.28it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 31.65it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:05, 29.50it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 29.45it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:04, 31.58it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 22.44it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:06, 21.48it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 27.63it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 26.84it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:03, 29.62it/s] Loading 0: 69%|██████▉ | 250/363 [00:09<00:04, 28.17it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 29.97it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 28.56it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 22.94it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 20.37it/s] Loading 0: 75%|███████▌ | 273/363 [00:10<00:03, 27.15it/s] Loading 0: 76%|███████▌ | 276/363 [00:10<00:03, 25.52it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 30.71it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 29.93it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 32.24it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 30.63it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 31.24it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 26.88it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 24.72it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 23.41it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 30.35it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 28.94it/s] Loading 0: 90%|█████████ | 327/363 [00:11<00:01, 31.90it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 30.51it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 32.45it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.38it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.98it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.66it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.85it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 4.98it/s]
Job chaiml-0918-horror-retor-3693-v3-mkmlizer completed after 177.68s with status: succeeded
Stopping job with name chaiml-0918-horror-retor-3693-v3-mkmlizer
Pipeline stage MKMLizer completed in 179.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-0918-horror-retor-3693-v3
Waiting for inference service chaiml-0918-horror-retor-3693-v3 to be ready
Failed to get response for submission zonemercy-lexical-nemov8_5966_v9: ('http://chaiml-llama-8b-pairwis-8189-v27-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60048->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-0918-horror-retor-3693-v3 ready after 202.1868588924408s
Pipeline stage MKMLDeployer completed in 202.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.748181104660034s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.803692102432251s
Received healthy response to inference request in 1.7480356693267822s
Received healthy response to inference request in 2.3174281120300293s
Received healthy response to inference request in 2.3121402263641357s
5 requests
0 failed requests
5th percentile: 1.759166955947876
10th percentile: 1.7702982425689697
20th percentile: 1.7925608158111572
30th percentile: 1.905381727218628
40th percentile: 2.1087609767913817
50th percentile: 2.3121402263641357
60th percentile: 2.314255380630493
70th percentile: 2.3163705348968504
80th percentile: 2.4035787105560305
90th percentile: 2.5758799076080323
95th percentile: 2.662030506134033
99th percentile: 2.730950984954834
mean time: 2.1858954429626465
Pipeline stage StressChecker completed in 11.70s
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 4.47s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_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 chaiml-0918-horror-retor-3693-v3-profiler
Waiting for inference service chaiml-0918-horror-retor-3693-v3-profiler to be ready
Inference service chaiml-0918-horror-retor-3693-v3-profiler ready after 190.48607778549194s
Pipeline stage MKMLProfilerDeployer completed in 190.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-0918-horror-r12f816461186f35a74b053159917c119-deplopfxtb:/code/chaiverse_profiler_1726774761 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-0918-horror-r12f816461186f35a74b053159917c119-deplopfxtb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726774761 && python profiles.py profile --best_of_n 4 --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_1726774761/summary.json'
kubectl exec -it chaiml-0918-horror-r12f816461186f35a74b053159917c119-deplopfxtb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726774761/summary.json'
Pipeline stage MKMLProfilerRunner completed in 966.06s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-0918-horror-retor-3693-v3-profiler is running
Tearing down inference service chaiml-0918-horror-retor-3693-v3-profiler
Service chaiml-0918-horror-retor-3693-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.25s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-0918-horror-retor_3693_v3 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0919-virgo-top-bo_9526_v1
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 3.63s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
chaiml-0918-horror-retor_3693_v3 status is now torndown due to DeploymentManager action
run pipeline stage %s
run pipeline stage %s
run pipeline %s
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0919-virgo-top-bo_9526_v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 5.91s
chaiml-0918-horror-retor_3693_v3 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_v3 status is now torndown due to DeploymentManager action
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0918-horror-retor_3693_v3
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0918-null-sft-albert_v2
Running pipeline stage MKMLDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLDeleter completed in 1.01s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 0.81s
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 0.86s
Pipeline stage MKMLModelDeleter completed in 0.86s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 0.74s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.63s
Shutdown handler de-registered
Shutdown handler de-registered
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_v3 status is now torndown due to DeploymentManager action
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0919-virgo-top-bo_9526_v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 7.80s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler de-registered
nousresearch-meta-llama-4939-v63-mkmlizer: ║ _____ __ __ ║
Pipeline stage MKMLModelDeleter completed in 6.48s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-albert-0917-sft-b_8477_v2