developer_uid: zonemercy
submission_id: chaiml-snugstable1-5-12_76771_v4
model_name: tempv1-3
model_group: ChaiML/SnugStable1.5-12b
status: torndown
timestamp: 2025-01-05T15:37:29+00:00
num_battles: 13850
num_wins: 7451
celo_rating: 1294.46
family_friendly_score: 0.5932
family_friendly_standard_error: 0.006947139843129689
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': 0.6525524329222658, 'latency_mean': 1.5323572218418122, 'latency_p50': 1.5332660675048828, 'latency_p90': 1.6898828983306884}, {'batch_size': 3, 'throughput': 1.2672264440705763, 'latency_mean': 2.3623951935768126, 'latency_p50': 2.3503140211105347, 'latency_p90': 2.625708413124084}, {'batch_size': 5, 'throughput': 1.5658489136809857, 'latency_mean': 3.1664090538024903, 'latency_p50': 3.157788395881653, 'latency_p90': 3.5516725540161134}, {'batch_size': 6, 'throughput': 1.669959192145599, 'latency_mean': 3.57728062748909, 'latency_p50': 3.6028952598571777, 'latency_p90': 4.006675219535827}, {'batch_size': 8, 'throughput': 1.7500668833634025, 'latency_mean': 4.537558214664459, 'latency_p50': 4.504993557929993, 'latency_p90': 5.121671199798584}, {'batch_size': 10, 'throughput': 1.7990328844565486, 'latency_mean': 5.510614337921143, 'latency_p50': 5.549033522605896, 'latency_p90': 6.13883147239685}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-3
is_internal_developer: True
language_model: ChaiML/SnugStable1.5-12b0-l1e5r7b4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.69
us_pacific_date: 2025-01-05
win_ratio: 0.5379783393501805
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', 'You:', '<|eot_id|>', 'Bot:', 'User:', '<|im_end|>', '</s>', '####'], '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-v4-mkmlizer
Waiting for job on chaiml-snugstable1-5-12-76771-v4-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ /___/ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ║ ║
chaiml-snugstable1-5-12-76771-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-5-12-76771-v4-mkmlizer: Downloaded to shared memory in 33.835s
chaiml-snugstable1-5-12-76771-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5optlej5, device:0
chaiml-snugstable1-5-12-76771-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-12-76771-v4-mkmlizer: quantized model in 37.153s
chaiml-snugstable1-5-12-76771-v4-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7b4 in 70.989s
chaiml-snugstable1-5-12-76771-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-12-76771-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-12-76771-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v4
chaiml-snugstable1-5-12-76771-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v4/config.json
chaiml-snugstable1-5-12-76771-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v4/special_tokens_map.json
chaiml-snugstable1-5-12-76771-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v4/tokenizer_config.json
chaiml-snugstable1-5-12-76771-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v4/tokenizer.json
chaiml-snugstable1-5-12-76771-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.48it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 45.90it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 48.11it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 39.72it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 46.12it/s] Loading 0: 10%|▉ | 36/363 [00:00<00:07, 46.59it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:08, 37.29it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:07, 44.20it/s] Loading 0: 15%|█▍ | 53/363 [00:01<00:07, 41.39it/s] Loading 0: 16%|█▌ | 58/363 [00:01<00:07, 41.61it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:10, 28.00it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:10, 29.19it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 30.95it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 31.97it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 36.21it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:07, 35.86it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 40.29it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:06, 42.50it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 34.52it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:07, 36.84it/s] Loading 0: 30%|███ | 110/363 [00:02<00:06, 38.22it/s] Loading 0: 32%|███▏ | 115/363 [00:03<00:06, 39.88it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:06, 36.13it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 38.90it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 40.78it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 42.96it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 41.63it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.63it/s] Loading 0: 41%|████▏ | 150/363 [00:04<00:06, 30.75it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 36.98it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 38.00it/s] Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 37.43it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.65it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.41it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 45.53it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 50.48it/s] Loading 0: 55%|█████▍ | 199/363 [00:05<00:03, 47.99it/s] Loading 0: 56%|█████▌ | 204/363 [00:05<00:03, 45.72it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 50.24it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.54it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 45.86it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 33.47it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.95it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 39.78it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:02, 40.51it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 39.08it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 43.45it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 43.50it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.74it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.77it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 43.27it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:01, 47.36it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 46.21it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 45.96it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 45.42it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 45.34it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:24, 2.32it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.21it/s] Loading 0: 87%|████████▋ | 317/363 [00:14<00:10, 4.41it/s] Loading 0: 88%|████████▊ | 321/363 [00:14<00:07, 5.51it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 7.49it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 9.00it/s] Loading 0: 92%|█████████▏| 335/363 [00:15<00:02, 11.89it/s] Loading 0: 93%|█████████▎| 339/363 [00:15<00:01, 13.40it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 17.47it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 19.51it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 27.00it/s] Loading 0: 99%|█████████▉| 360/363 [00:16<00:00, 29.58it/s]
Job chaiml-snugstable1-5-12-76771-v4-mkmlizer completed after 104.93s with status: succeeded
Stopping job with name chaiml-snugstable1-5-12-76771-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.43s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.77s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-5-12-76771-v4
Waiting for inference service chaiml-snugstable1-5-12-76771-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-snugstable1-5-12-76771-v4 ready after 341.7221658229828s
Pipeline stage MKMLDeployer completed in 342.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7126553058624268s
Received healthy response to inference request in 1.4473075866699219s
Received healthy response to inference request in 0.977931022644043s
Received healthy response to inference request in 1.4137835502624512s
Received healthy response to inference request in 0.8867638111114502s
5 requests
0 failed requests
5th percentile: 0.9049972534179688
10th percentile: 0.9232306957244873
20th percentile: 0.9596975803375244
30th percentile: 1.0651015281677245
40th percentile: 1.2394425392150878
50th percentile: 1.4137835502624512
60th percentile: 1.4271931648254395
70th percentile: 1.4406027793884277
80th percentile: 1.5003771305084228
90th percentile: 1.606516218185425
95th percentile: 1.6595857620239258
99th percentile: 1.7020413970947266
mean time: 1.2876882553100586
Pipeline stage StressChecker completed in 7.80s
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 0.66s
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 0.80s
Shutdown handler de-registered
chaiml-snugstable1-5-12_76771_v4 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 2828.75s
Shutdown handler de-registered
chaiml-snugstable1-5-12_76771_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-12_76771_v4 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12_76771_v4 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12_76771_v4 status is now torndown due to DeploymentManager action