developer_uid: zonemercy
submission_id: chaiml-snugstable1-1-12b_2625_v1
model_name: tempv1-2
model_group: ChaiML/SnugStable1.1-12b
status: torndown
timestamp: 2024-12-26T10:30:52+00:00
num_battles: 20611
num_wins: 11313
celo_rating: 1300.45
family_friendly_score: 0.5702
family_friendly_standard_error: 0.007001027924526513
submission_type: basic
model_repo: ChaiML/SnugStable1.1-12b0-1e5r128
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6399368119033279, 'latency_mean': 1.5625965785980225, 'latency_p50': 1.5712045431137085, 'latency_p90': 1.7305504560470581}, {'batch_size': 3, 'throughput': 1.254119861894394, 'latency_mean': 2.383194878101349, 'latency_p50': 2.3924176692962646, 'latency_p90': 2.5818639516830446}, {'batch_size': 5, 'throughput': 1.592529767896611, 'latency_mean': 3.116598666906357, 'latency_p50': 3.0942386388778687, 'latency_p90': 3.487014889717102}, {'batch_size': 6, 'throughput': 1.693645143243486, 'latency_mean': 3.514740356206894, 'latency_p50': 3.5059391260147095, 'latency_p90': 3.941599488258362}, {'batch_size': 8, 'throughput': 1.858288534816162, 'latency_mean': 4.268135478496552, 'latency_p50': 4.266438007354736, 'latency_p90': 4.846746158599854}, {'batch_size': 10, 'throughput': 1.9372545811098918, 'latency_mean': 5.1260143303871155, 'latency_p50': 5.1245341300964355, 'latency_p90': 5.775358748435974}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-2
is_internal_developer: True
language_model: ChaiML/SnugStable1.1-12b0-1e5r128
model_size: 13B
ranking_group: single
throughput_3p7s: 1.75
us_pacific_date: 2024-12-26
win_ratio: 0.5488816651302703
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>', 'Bot:', '<|im_end|>', 'You:', '<|eot_id|>', 'User:', '####'], 'max_input_tokens': 1024, 'best_of': 4, '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-snugstable1-1-12b-2625-v1-mkmlizer
Waiting for job on chaiml-snugstable1-1-12b-2625-v1-mkmlizer to finish
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ /___/ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ║ ║
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: Downloaded to shared memory in 46.071s
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnjqtrvv8, device:0
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: quantized model in 38.837s
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: Processed model ChaiML/SnugStable1.1-12b0-1e5r128 in 84.908s
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-1-12b-2625-v1
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-1-12b-2625-v1/config.json
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-1-12b-2625-v1/special_tokens_map.json
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-1-12b-2625-v1/tokenizer_config.json
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-1-12b-2625-v1/tokenizer.json
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-1-12b-2625-v1/flywheel_model.0.safetensors
chaiml-snugstable1-1-12b-2625-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 23.95it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:10, 34.39it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:11, 30.22it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:09, 35.87it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:10, 32.23it/s] Loading 0: 8%|▊ | 28/363 [00:00<00:09, 36.63it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 31.90it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 40.07it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:08, 39.78it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 39.80it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 40.29it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 41.51it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:11, 25.09it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 32.05it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 33.30it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 35.27it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 37.46it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 31.57it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.11it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 37.88it/s] Loading 0: 30%|██▉ | 108/363 [00:03<00:06, 38.57it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 32.40it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 33.06it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 40.03it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 39.37it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 39.70it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 41.41it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 26.15it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 26.19it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 33.66it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 34.72it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 36.51it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:05, 37.84it/s] Loading 0: 48%|████▊ | 176/363 [00:05<00:05, 31.65it/s] Loading 0: 50%|████▉ | 181/363 [00:05<00:05, 35.35it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:05, 31.97it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 38.75it/s] Loading 0: 54%|█████▍ | 197/363 [00:05<00:04, 37.32it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 35.69it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 34.33it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 37.37it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 35.43it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 35.00it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 25.24it/s] Loading 0: 62%|██████▏ | 226/363 [00:06<00:05, 24.96it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:05, 25.41it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.12it/s] Loading 0: 66%|██████▋ | 241/363 [00:07<00:03, 33.32it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 36.20it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.13it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 37.15it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.72it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 38.69it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 37.05it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 39.97it/s] Loading 0: 77%|███████▋ | 278/363 [00:08<00:02, 38.19it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 38.39it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 36.51it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 38.55it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 36.59it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 37.38it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:28, 2.10it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.63it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:13, 3.86it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:07, 6.26it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.83it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.49it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:02, 12.65it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:01, 16.38it/s] Loading 0: 94%|█████████▍| 341/363 [00:16<00:01, 18.73it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 22.94it/s] Loading 0: 96%|█████████▋| 350/363 [00:16<00:00, 24.71it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 28.69it/s] Loading 0: 99%|█████████▉| 359/363 [00:16<00:00, 29.12it/s]
Job chaiml-snugstable1-1-12b-2625-v1-mkmlizer completed after 114.83s with status: succeeded
Stopping job with name chaiml-snugstable1-1-12b-2625-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-1-12b-2625-v1
Waiting for inference service chaiml-snugstable1-1-12b-2625-v1 to be ready
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
Inference service chaiml-snugstable1-1-12b-2625-v1 ready after 281.7398154735565s
Pipeline stage MKMLDeployer completed in 282.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2421481609344482s
Received healthy response to inference request in 1.3300621509552002s
Received healthy response to inference request in 1.146939992904663s
Received healthy response to inference request in 1.5478579998016357s
Received healthy response to inference request in 1.8159728050231934s
5 requests
0 failed requests
5th percentile: 1.1835644245147705
10th percentile: 1.220188856124878
20th percentile: 1.2934377193450928
30th percentile: 1.3736213207244874
40th percentile: 1.4607396602630616
50th percentile: 1.5478579998016357
60th percentile: 1.6551039218902588
70th percentile: 1.7623498439788818
80th percentile: 1.9012078762054445
90th percentile: 2.0716780185699464
95th percentile: 2.156913089752197
99th percentile: 2.225101146697998
mean time: 1.6165962219238281
Pipeline stage StressChecker completed in 9.46s
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 0.70s
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-snugstable1-1-12b_2625_v1 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 2668.98s
Shutdown handler de-registered
chaiml-snugstable1-1-12b_2625_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-1-12b_2625_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable1-1-12b_2625_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable1-1-12b_2625_v1 status is now torndown due to DeploymentManager action