chaiml-snugstable1-5-12_76771

developer_uid: zonemercy

submission_id: chaiml-snugstable1-5-12_76771_v8

model_name: tempv1-2

model_group: ChaiML/SnugStable1.5-12b

status: torndown

timestamp: 2025-01-07T23:27:50+00:00

num_battles: 6841

num_wins: 3604

celo_rating: 1295.54

family_friendly_score: 0.5900000000000001

family_friendly_standard_error: 0.0069555733049116815

submission_type: basic

model_repo: ChaiML/SnugStable1.5-12b0-l1e5r7b4

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6579933340458358, 'latency_mean': 1.519676263332367, 'latency_p50': 1.5192888975143433, 'latency_p90': 1.672537589073181}, {'batch_size': 3, 'throughput': 1.276764711807048, 'latency_mean': 2.3353059780597687, 'latency_p50': 2.3192628622055054, 'latency_p90': 2.583729124069214}, {'batch_size': 5, 'throughput': 1.6110138129678275, 'latency_mean': 3.0852161622047425, 'latency_p50': 3.0630327463150024, 'latency_p90': 3.464506196975708}, {'batch_size': 6, 'throughput': 1.6856866040591076, 'latency_mean': 3.548159314393997, 'latency_p50': 3.5656384229660034, 'latency_p90': 4.009666585922242}, {'batch_size': 8, 'throughput': 1.7919325805053343, 'latency_mean': 4.43011066198349, 'latency_p50': 4.457139611244202, 'latency_p90': 4.935258674621582}, {'batch_size': 10, 'throughput': 1.8556598589296363, 'latency_mean': 5.342474439144135, 'latency_p50': 5.351671576499939, 'latency_p90': 6.031860995292663}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-2

is_internal_developer: True

language_model: ChaiML/SnugStable1.5-12b0-l1e5r7b4

model_size: 13B

ranking_group: single

throughput_3p7s: 1.71

us_pacific_date: 2025-01-07

win_ratio: 0.526823563806461

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': ['####', '<|eot_id|>', '\n', '</s>', 'Bot:', '<|im_end|>', 'You:', 'User:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}

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-snugstable1-5-12-76771-v8-mkmlizer
Waiting for job on chaiml-snugstable1-5-12-76771-v8-mkmlizer to finish
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-5-12-76771-v8-mkmlizer: Downloaded to shared memory in 33.976s
chaiml-snugstable1-5-12-76771-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkq0n8zp5, device:0
chaiml-snugstable1-5-12-76771-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-12-76771-v8-mkmlizer: quantized model in 38.593s
chaiml-snugstable1-5-12-76771-v8-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7b4 in 72.569s
chaiml-snugstable1-5-12-76771-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-12-76771-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-12-76771-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v8
chaiml-snugstable1-5-12-76771-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v8/config.json
chaiml-snugstable1-5-12-76771-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v8/special_tokens_map.json
chaiml-snugstable1-5-12-76771-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v8/tokenizer_config.json
chaiml-snugstable1-5-12-76771-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v8/tokenizer.json
chaiml-snugstable1-5-12-76771-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v8/flywheel_model.0.safetensors
chaiml-snugstable1-5-12-76771-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.20it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.82it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.10it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.49it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.64it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.01it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.73it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.02it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 47.25it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:07, 42.59it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 26.82it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:10, 28.99it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:10, 28.62it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 36.28it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 35.86it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:07, 36.25it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:07, 35.59it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 36.49it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 35.40it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 35.93it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:06, 40.68it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 37.95it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 37.30it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 37.59it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.25it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 37.07it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.13it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:09, 23.97it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 23.85it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 24.58it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 29.84it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 29.04it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.45it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 37.59it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 38.31it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:04, 39.36it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 31.92it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.45it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 38.43it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:04, 38.43it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 39.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 32.66it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 36.92it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 28.84it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.04it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 26.50it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 31.75it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 32.21it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 35.00it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 34.22it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 36.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.65it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 38.35it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 36.31it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.51it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 36.43it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 38.71it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 35.87it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 37.89it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 35.78it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 34.49it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:28,  2.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.57it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.79it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  6.17it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.77it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:03, 10.49it/s]
Loading 0:  92%|█████████▏| 333/363 [00:16<00:02, 13.51it/s]
Loading 0:  93%|█████████▎| 338/363 [00:16<00:01, 16.95it/s]
Loading 0:  94%|█████████▍| 343/363 [00:16<00:00, 20.95it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 21.04it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 27.87it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 31.36it/s]
                                                            
Job chaiml-snugstable1-5-12-76771-v8-mkmlizer completed after 125.0s with status: succeeded
Stopping job with name chaiml-snugstable1-5-12-76771-v8-mkmlizer
Pipeline stage MKMLizer completed in 125.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-5-12-76771-v8
Waiting for inference service chaiml-snugstable1-5-12-76771-v8 to be ready
Inference service chaiml-snugstable1-5-12-76771-v8 ready after 351.6875879764557s
Pipeline stage MKMLDeployer completed in 352.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4757826328277588s
Received healthy response to inference request in 0.9246082305908203s
Received healthy response to inference request in 1.628563642501831s
Received healthy response to inference request in 1.5268921852111816s
Received healthy response to inference request in 1.4338836669921875s
5 requests
0 failed requests
5th percentile: 1.0264633178710938
10th percentile: 1.1283184051513673
20th percentile: 1.332028579711914
30th percentile: 1.4422634601593018
40th percentile: 1.4590230464935303
50th percentile: 1.4757826328277588
60th percentile: 1.4962264537811278
70th percentile: 1.5166702747344971
80th percentile: 1.5472264766693116
90th percentile: 1.5878950595855712
95th percentile: 1.6082293510437011
99th percentile: 1.6244967842102052
mean time: 1.3979460716247558
Pipeline stage StressChecker completed in 8.97s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.63s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.63s
Shutdown handler de-registered
chaiml-snugstable1-5-12_76771_v8 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2531.75s
Shutdown handler de-registered
chaiml-snugstable1-5-12_76771_v8 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-12_76771_v8 status is now torndown due to DeploymentManager action