chaiml-horror-sft-v1-5e6

developer_uid: zonemercy

submission_id: chaiml-horror-sft-v1-5e6_v3

model_name: chaiml-horror-sft-v1-5e6_v3

model_group: ChaiML/Horror-SFT-v1-5e6

status: torndown

timestamp: 2024-09-05T21:03:00+00:00

num_battles: 12297

num_wins: 6274

celo_rating: 1241.6

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/Horror-SFT-v1-5e6

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6364816591204683, 'latency_mean': 1.5710647106170654, 'latency_p50': 1.5735450983047485, 'latency_p90': 1.7304800271987915}, {'batch_size': 3, 'throughput': 1.2480695379417865, 'latency_mean': 2.3920502138137816, 'latency_p50': 2.376415491104126, 'latency_p90': 2.6179680585861207}, {'batch_size': 5, 'throughput': 1.536682529400699, 'latency_mean': 3.2243780660629273, 'latency_p50': 3.2072077989578247, 'latency_p90': 3.6637288093566895}, {'batch_size': 6, 'throughput': 1.6308224852486972, 'latency_mean': 3.659588265419006, 'latency_p50': 3.655148148536682, 'latency_p90': 4.10902955532074}, {'batch_size': 8, 'throughput': 1.7489307167759685, 'latency_mean': 4.547731597423553, 'latency_p50': 4.557693004608154, 'latency_p90': 5.167786192893982}, {'batch_size': 10, 'throughput': 1.8015270344165857, 'latency_mean': 5.516252830028534, 'latency_p50': 5.490433096885681, 'latency_p90': 6.300631427764893}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-horror-sft-v1-5e6_v3

is_internal_developer: True

language_model: ChaiML/Horror-SFT-v1-5e6

model_size: 13B

ranking_group: single

throughput_3p7s: 1.65

us_pacific_date: 2024-09-05

win_ratio: 0.5102057412377002

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>', 'You:', 'Bot:', 'User:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\nMake the conversation as scary as possible while keep in character\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}

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-horror-sft-v1-5e6-v3-mkmlizer
Waiting for job on chaiml-horror-sft-v1-5e6-v3-mkmlizer to finish
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║       /___/                                                         ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-horror-sft-v1-5e6-v3-mkmlizer: ║                                                                     ║
chaiml-horror-sft-v1-5e6-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
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 blend_jitik_2024-08-26: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:46356->127.0.0.1:8080: write tcp 127.0.0.1:46356->127.0.0.1:8080: use of closed network connection\n')
Failed to get response for submission blend_katim_2024-08-22: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54914->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
Failed to get response for submission blend_sehof_2024-08-22: ('http://mistralai-mixtral-8x7b-3473-v130-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:59308->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-horror-sft-v1-5e6-v3-mkmlizer: Downloaded to shared memory in 995.076s
chaiml-horror-sft-v1-5e6-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_5k3k3vq, device:0
chaiml-horror-sft-v1-5e6-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-horror-sft-v1-5e6-v3-mkmlizer: quantized model in 34.859s
chaiml-horror-sft-v1-5e6-v3-mkmlizer: Processed model ChaiML/Horror-SFT-v1-5e6 in 1029.936s
chaiml-horror-sft-v1-5e6-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-horror-sft-v1-5e6-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e6-v3
chaiml-horror-sft-v1-5e6-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e6-v3/config.json
chaiml-horror-sft-v1-5e6-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e6-v3/special_tokens_map.json
chaiml-horror-sft-v1-5e6-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e6-v3/tokenizer_config.json
chaiml-horror-sft-v1-5e6-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-horror-sft-v1-5e6-v3/tokenizer.json
chaiml-horror-sft-v1-5e6-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.20it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.38it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 49.30it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:07, 47.78it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.35it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 49.39it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 51.40it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.74it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.62it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.83it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.06it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.12it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.54it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 48.29it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.21it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.92it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.07it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 48.15it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 46.67it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 46.92it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 45.32it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 44.14it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.64it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:05, 36.30it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 35.18it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.64it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.74it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 43.00it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 48.28it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 46.41it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.13it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.11it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 47.73it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.78it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 50.81it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.64it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.82it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.85it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 37.28it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 42.52it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 42.20it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.61it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 44.46it/s]
Loading 0:  72%|███████▏  | 260/363 [00:05<00:02, 43.61it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.13it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 43.94it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 42.95it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 48.26it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 45.32it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 43.42it/s]
Loading 0:  83%|████████▎ | 302/363 [00:06<00:01, 51.90it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:18,  2.93it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:13,  3.65it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:07,  5.73it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:04,  7.65it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.70it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.68it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.06it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 20.23it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.42it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 29.70it/s]
                                                            
Job chaiml-horror-sft-v1-5e6-v3-mkmlizer completed after 1057.59s with status: succeeded
Stopping job with name chaiml-horror-sft-v1-5e6-v3-mkmlizer
Pipeline stage MKMLizer completed in 1058.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-horror-sft-v1-5e6-v3
Waiting for inference service chaiml-horror-sft-v1-5e6-v3 to be ready
Inference service chaiml-horror-sft-v1-5e6-v3 ready after 150.83807110786438s
Pipeline stage MKMLDeployer completed in 151.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.919032335281372s
Received healthy response to inference request in 2.1991512775421143s
Received healthy response to inference request in 1.7585468292236328s
Received healthy response to inference request in 1.6597518920898438s
Received healthy response to inference request in 2.640022039413452s
5 requests
0 failed requests
5th percentile: 1.6795108795166016
10th percentile: 1.6992698669433595
20th percentile: 1.738787841796875
30th percentile: 1.846667718887329
40th percentile: 2.0229094982147218
50th percentile: 2.1991512775421143
60th percentile: 2.3754995822906495
70th percentile: 2.5518478870391843
80th percentile: 2.6958240985870363
90th percentile: 2.807428216934204
95th percentile: 2.863230276107788
99th percentile: 2.9078719234466552
mean time: 2.235300874710083
Pipeline stage StressChecker completed in 12.30s
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 6.16s
Shutdown handler de-registered
chaiml-horror-sft-v1-5e6_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-horror-sft-v1-5e6-v3-profiler
Waiting for inference service chaiml-horror-sft-v1-5e6-v3-profiler to be ready
Inference service chaiml-horror-sft-v1-5e6-v3-profiler ready after 150.43987011909485s
Pipeline stage MKMLProfilerDeployer completed in 150.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-horror-sft-v1-5e6-v3-profiler-predictor-00001-deplo88pb9:/code/chaiverse_profiler_1725571600 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-horror-sft-v1-5e6-v3-profiler-predictor-00001-deplo88pb9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725571600 && 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_1725571600/summary.json'
kubectl exec -it chaiml-horror-sft-v1-5e6-v3-profiler-predictor-00001-deplo88pb9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725571600/summary.json'
Pipeline stage MKMLProfilerRunner completed in 957.94s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-horror-sft-v1-5e6-v3-profiler is running
Tearing down inference service chaiml-horror-sft-v1-5e6-v3-profiler
Service chaiml-horror-sft-v1-5e6-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.66s
Shutdown handler de-registered
chaiml-horror-sft-v1-5e6_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-horror-sft-v1-5e6_v3 status is now torndown due to DeploymentManager action