developer_uid: zonemercy
submission_id: chaiml-snugstable1-4-12_11636_v5
model_name: tempv1-3
model_group: ChaiML/SnugStable1.4-12b
status: torndown
timestamp: 2025-01-02T04:08:11+00:00
num_battles: 15007
num_wins: 8182
celo_rating: 1304.34
family_friendly_score: 0.5788
family_friendly_standard_error: 0.006982700910106346
submission_type: basic
model_repo: ChaiML/SnugStable1.4-12b0-l1e5r7
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': 0.6533256271938537, 'latency_mean': 1.5305575704574585, 'latency_p50': 1.533270239830017, 'latency_p90': 1.6788642168045045}, {'batch_size': 3, 'throughput': 1.2746531745806786, 'latency_mean': 2.348249479532242, 'latency_p50': 2.341500163078308, 'latency_p90': 2.59377179145813}, {'batch_size': 5, 'throughput': 1.581294129044068, 'latency_mean': 3.143026419878006, 'latency_p50': 3.1551250219345093, 'latency_p90': 3.5144628286361694}, {'batch_size': 6, 'throughput': 1.6795960728868395, 'latency_mean': 3.5472195303440093, 'latency_p50': 3.558497905731201, 'latency_p90': 3.9320637702941896}, {'batch_size': 8, 'throughput': 1.778902387100827, 'latency_mean': 4.466133488416672, 'latency_p50': 4.504364967346191, 'latency_p90': 5.007706212997436}, {'batch_size': 10, 'throughput': 1.8381335036190485, 'latency_mean': 5.4103847289085385, 'latency_p50': 5.434358716011047, 'latency_p90': 6.086849808692932}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-3
is_internal_developer: True
language_model: ChaiML/SnugStable1.4-12b0-l1e5r7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.71
us_pacific_date: 2025-01-01
win_ratio: 0.5452122342906643
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', 'Bot:', '\n', '<|eot_id|>', '####', 'You:', 'User:', '</s>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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-snugstable1-4-12-11636-v5-mkmlizer
Waiting for job on chaiml-snugstable1-4-12-11636-v5-mkmlizer to finish
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ /___/ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-4-12-11636-v5-mkmlizer: Downloaded to shared memory in 44.990s
chaiml-snugstable1-4-12-11636-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb_q1qr2f, device:0
chaiml-snugstable1-4-12-11636-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-4-12-11636-v5-mkmlizer: quantized model in 40.044s
chaiml-snugstable1-4-12-11636-v5-mkmlizer: Processed model ChaiML/SnugStable1.4-12b0-l1e5r7 in 85.034s
chaiml-snugstable1-4-12-11636-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-4-12-11636-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-4-12-11636-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v5
chaiml-snugstable1-4-12-11636-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v5/config.json
chaiml-snugstable1-4-12-11636-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v5/special_tokens_map.json
chaiml-snugstable1-4-12-11636-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v5/tokenizer_config.json
chaiml-snugstable1-4-12-11636-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v5/tokenizer.json
chaiml-snugstable1-4-12-11636-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v5/flywheel_model.0.safetensors
chaiml-snugstable1-4-12-11636-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.87it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:10, 34.24it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:11, 30.29it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:08, 40.61it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:08, 40.68it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:08, 38.96it/s] Loading 0: 10%|▉ | 36/363 [00:00<00:08, 38.50it/s] Loading 0: 11%|█ | 40/363 [00:01<00:08, 36.72it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:07, 39.89it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:09, 33.33it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:07, 38.59it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:10, 29.02it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 28.15it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:09, 30.42it/s] Loading 0: 20%|██ | 73/363 [00:02<00:10, 28.95it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 36.87it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:07, 35.62it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 35.35it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:08, 33.66it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 35.51it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 33.91it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 33.35it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 37.05it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:07, 34.10it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 32.66it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 35.06it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 33.95it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 35.99it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 34.07it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:09, 24.23it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:10, 19.97it/s] Loading 0: 41%|████ | 149/363 [00:04<00:10, 21.35it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:07, 29.32it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 29.80it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 32.83it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 32.28it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 35.14it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 34.04it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:05, 35.92it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:05, 33.86it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 35.59it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:05, 31.69it/s] Loading 0: 55%|█████▌ | 201/363 [00:06<00:04, 33.98it/s] Loading 0: 56%|█████▋ | 205/363 [00:06<00:04, 32.98it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 35.34it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 33.66it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 33.97it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 26.98it/s] Loading 0: 62%|██████▏ | 226/363 [00:07<00:05, 26.20it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:05, 25.62it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 30.58it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 29.30it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 36.90it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.23it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 37.54it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.58it/s] Loading 0: 73%|███████▎ | 264/363 [00:08<00:02, 37.91it/s] Loading 0: 74%|███████▍ | 268/363 [00:08<00:02, 35.60it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 38.06it/s] Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 34.79it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 37.47it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 35.46it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 38.20it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 35.58it/s] Loading 0: 82%|████████▏ | 299/363 [00:09<00:01, 35.15it/s] Loading 0: 83%|████████▎ | 303/363 [00:09<00:01, 36.16it/s] Loading 0: 85%|████████▍ | 307/363 [00:16<00:30, 1.84it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:18, 2.71it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:09, 4.43it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:07, 5.63it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:04, 7.70it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:03, 9.58it/s] Loading 0: 93%|█████████▎| 337/363 [00:17<00:02, 12.77it/s] Loading 0: 94%|█████████▍| 341/363 [00:17<00:01, 15.10it/s] Loading 0: 95%|█████████▌| 346/363 [00:17<00:00, 19.11it/s] Loading 0: 96%|█████████▋| 350/363 [00:17<00:00, 21.11it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 25.17it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 26.43it/s]
Job chaiml-snugstable1-4-12-11636-v5-mkmlizer completed after 114.57s with status: succeeded
Stopping job with name chaiml-snugstable1-4-12-11636-v5-mkmlizer
Pipeline stage MKMLizer completed in 115.05s
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-snugstable1-4-12-11636-v5
Waiting for inference service chaiml-snugstable1-4-12-11636-v5 to be ready
Inference service chaiml-snugstable1-4-12-11636-v5 ready after 331.2953517436981s
Pipeline stage MKMLDeployer completed in 331.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8833975791931152s
Received healthy response to inference request in 1.5376458168029785s
Received healthy response to inference request in 1.467411994934082s
Received healthy response to inference request in 1.2393031120300293s
Received healthy response to inference request in 1.3801627159118652s
5 requests
0 failed requests
5th percentile: 1.2674750328063964
10th percentile: 1.2956469535827637
20th percentile: 1.3519907951354981
30th percentile: 1.3976125717163086
40th percentile: 1.4325122833251953
50th percentile: 1.467411994934082
60th percentile: 1.4955055236816406
70th percentile: 1.5235990524291991
80th percentile: 1.606796169281006
90th percentile: 1.7450968742370605
95th percentile: 1.8142472267150878
99th percentile: 1.8695675086975097
mean time: 1.501584243774414
Pipeline stage StressChecker completed in 8.83s
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 0.65s
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 0.68s
Shutdown handler de-registered
chaiml-snugstable1-4-12_11636_v5 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 2530.50s
Shutdown handler de-registered
chaiml-snugstable1-4-12_11636_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-4-12_11636_v5 status is now torndown due to DeploymentManager action
chaiml-snugstable1-4-12_11636_v5 status is now torndown due to DeploymentManager action
chaiml-snugstable1-4-12_11636_v5 status is now torndown due to DeploymentManager action