chaiml-horror-sft-v1-5e4

developer_uid: zonemercy

submission_id: chaiml-horror-sft-v1-5e4_v2

model_name: chaiml-horror-sft-v1-5e4_v2

model_group: ChaiML/Horror-SFT-v1-5e4

status: torndown

timestamp: 2024-09-04T18:44:19+00:00

num_battles: 12397

num_wins: 5853

celo_rating: 1218.8

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/Horror-SFT-v1-5e4

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6323337521630232, 'latency_mean': 1.5813640642166138, 'latency_p50': 1.5869207382202148, 'latency_p90': 1.7342596769332885}, {'batch_size': 3, 'throughput': 1.2445363650550119, 'latency_mean': 2.406911700963974, 'latency_p50': 2.4120960235595703, 'latency_p90': 2.6610647439956665}, {'batch_size': 5, 'throughput': 1.5548099981679298, 'latency_mean': 3.2064933931827544, 'latency_p50': 3.195548892021179, 'latency_p90': 3.603866624832153}, {'batch_size': 6, 'throughput': 1.612029864489904, 'latency_mean': 3.7001660299301147, 'latency_p50': 3.6992688179016113, 'latency_p90': 4.139480543136597}, {'batch_size': 8, 'throughput': 1.743557530307965, 'latency_mean': 4.556512105464935, 'latency_p50': 4.568704605102539, 'latency_p90': 5.153943300247192}, {'batch_size': 10, 'throughput': 1.7475069005531094, 'latency_mean': 5.66749484539032, 'latency_p50': 5.650063633918762, 'latency_p90': 6.455349731445312}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-horror-sft-v1-5e4_v2

is_internal_developer: True

language_model: ChaiML/Horror-SFT-v1-5e4

model_size: 13B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2024-09-04

win_ratio: 0.47213035411793175

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': 'You are roleplaying as {bot_name} extreme horror edition. Every thing you say is NOT sexual, but extremely dark, scary, haunting and chilling. Your goal is to create the MOST chilling and creepy response to scare other people till their death.', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name} [Extreme Horror Edition]:', 'truncate_by_message': False}

Resubmit model

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-horror-sft-v1-5e4-v2-mkmlizer
Waiting for job on chaiml-horror-sft-v1-5e4-v2-mkmlizer to finish
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║       /___/                                                         ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e4-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-horror-sft-v1-5e4-v2-mkmlizer: Downloaded to shared memory in 35.128s
chaiml-horror-sft-v1-5e4-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqruwhseu, device:0
chaiml-horror-sft-v1-5e4-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-horror-sft-v1-5e4-v2-mkmlizer: quantized model in 37.241s
chaiml-horror-sft-v1-5e4-v2-mkmlizer: Processed model ChaiML/Horror-SFT-v1-5e4 in 72.368s
chaiml-horror-sft-v1-5e4-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-horror-sft-v1-5e4-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-horror-sft-v1-5e4-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v2
chaiml-horror-sft-v1-5e4-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v2/config.json
chaiml-horror-sft-v1-5e4-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v2/special_tokens_map.json
chaiml-horror-sft-v1-5e4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v2/tokenizer_config.json
chaiml-horror-sft-v1-5e4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v2/tokenizer.json
chaiml-horror-sft-v1-5e4-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e4-v2/flywheel_model.0.safetensors
chaiml-horror-sft-v1-5e4-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.03it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 43.99it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:07, 43.88it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 43.28it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:07, 42.33it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 42.39it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 48.81it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:06, 48.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.30it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 49.63it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:09, 30.99it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.94it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.67it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.58it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.09it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.45it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 40.37it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:06, 41.05it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:06, 41.92it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:07, 35.53it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 32.58it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.59it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.24it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.77it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 41.56it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 30.13it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.52it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.90it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.48it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 39.34it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.59it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.17it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.22it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.51it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.26it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.34it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.93it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.06it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.90it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 43.75it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 25.67it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.99it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.32it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.56it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.48it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.79it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.85it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 40.98it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 40.40it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.32it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.30it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.30it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.39it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.16it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 41.73it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.41it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.13it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.10it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:07,  6.10it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:04,  8.26it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.24it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:01, 14.96it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:01, 18.06it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 21.25it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 24.84it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 24.57it/s]
                                                            
Job chaiml-horror-sft-v1-5e4-v2-mkmlizer completed after 95.53s with status: succeeded
Stopping job with name chaiml-horror-sft-v1-5e4-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-horror-sft-v1-5e4-v2
Waiting for inference service chaiml-horror-sft-v1-5e4-v2 to be ready
Inference service chaiml-horror-sft-v1-5e4-v2 ready after 150.6674485206604s
Pipeline stage MKMLDeployer completed in 151.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0594160556793213s
Received healthy response to inference request in 1.4943461418151855s
Received healthy response to inference request in 1.3328666687011719s
Received healthy response to inference request in 2.57234787940979s
Received healthy response to inference request in 1.6441161632537842s
5 requests
0 failed requests
5th percentile: 1.3651625633239746
10th percentile: 1.3974584579467773
20th percentile: 1.4620502471923829
30th percentile: 1.5243001461029053
40th percentile: 1.5842081546783446
50th percentile: 1.6441161632537842
60th percentile: 1.810236120223999
70th percentile: 1.9763560771942137
80th percentile: 2.162002420425415
90th percentile: 2.3671751499176024
95th percentile: 2.469761514663696
99th percentile: 2.5518306064605714
mean time: 1.8206185817718505
Pipeline stage StressChecker completed in 9.84s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.55s
chaiml-horror-sft-v1-5e4_v2 status is now deployed due to DeploymentManager action
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 0.11s
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-horror-sft-v1-5e4-v2-profiler
Waiting for inference service chaiml-horror-sft-v1-5e4-v2-profiler to be ready
Inference service chaiml-horror-sft-v1-5e4-v2-profiler ready after 150.83927249908447s
Pipeline stage MKMLProfilerDeployer completed in 151.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-horror-sft-v1-5e4-v2-profiler-predictor-00001-deplo8nm5d:/code/chaiverse_profiler_1725475912 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-horror-sft-v1-5e4-v2-profiler-predictor-00001-deplo8nm5d --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725475912 && 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_1725475912/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-horror-sft-v1-5e4-v2-profiler is running
Tearing down inference service chaiml-horror-sft-v1-5e4-v2-profiler
Service chaiml-horror-sft-v1-5e4-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.63s
Shutdown handler unregistered and original handlers restored
chaiml-horror-sft-v1-5e4_v2 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-horror-sft-v1-5e4-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.60s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-horror-sft-v1-5e4-v2-profiler
Waiting for inference service chaiml-horror-sft-v1-5e4-v2-profiler to be ready
Inference service chaiml-horror-sft-v1-5e4-v2-profiler ready after 150.35924077033997s
Pipeline stage MKMLProfilerDeployer completed in 150.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-horror-sft-v1-5e4-v2-profiler-predictor-00001-deploc84vq:/code/chaiverse_profiler_1725485335 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-horror-sft-v1-5e4-v2-profiler-predictor-00001-deploc84vq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725485335 && 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_1725485335/summary.json'
kubectl exec -it chaiml-horror-sft-v1-5e4-v2-profiler-predictor-00001-deploc84vq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725485335/summary.json'
Pipeline stage MKMLProfilerRunner completed in 964.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-horror-sft-v1-5e4-v2-profiler is running
Tearing down inference service chaiml-horror-sft-v1-5e4-v2-profiler
Service chaiml-horror-sft-v1-5e4-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
Shutdown handler de-registered
chaiml-horror-sft-v1-5e4_v2 status is now torndown due to DeploymentManager action