developer_uid: zonemercy
submission_id: chaiml-snugstable1-4-12b_1163_v2
model_name: tempv1-5
model_group: ChaiML/SnugStable1.4-12b
status: torndown
timestamp: 2024-12-26T21:44:26+00:00
num_battles: 10889
num_wins: 5935
celo_rating: 1296.61
family_friendly_score: 0.5731999999999999
family_friendly_standard_error: 0.00699488041355962
submission_type: basic
model_repo: ChaiML/SnugStable1.4-12b0-l1e5r7
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': 0.6381626260358954, 'latency_mean': 1.56694256067276, 'latency_p50': 1.5694183111190796, 'latency_p90': 1.7346262693405152}, {'batch_size': 3, 'throughput': 1.2691613780983673, 'latency_mean': 2.357354885339737, 'latency_p50': 2.355161666870117, 'latency_p90': 2.5720481634140016}, {'batch_size': 5, 'throughput': 1.5874170175593387, 'latency_mean': 3.1320445907115935, 'latency_p50': 3.146138310432434, 'latency_p90': 3.5117770433425903}, {'batch_size': 6, 'throughput': 1.6914696999572216, 'latency_mean': 3.5395300257205964, 'latency_p50': 3.511110544204712, 'latency_p90': 3.9991999387741086}, {'batch_size': 8, 'throughput': 1.8453368166872124, 'latency_mean': 4.307284188270569, 'latency_p50': 4.295579791069031, 'latency_p90': 4.867787265777588}, {'batch_size': 10, 'throughput': 1.931962066108636, 'latency_mean': 5.135866205692292, 'latency_p50': 5.160046696662903, 'latency_p90': 5.823088002204895}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-5
is_internal_developer: True
language_model: ChaiML/SnugStable1.4-12b0-l1e5r7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-26
win_ratio: 0.545045458719809
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': ['</s>', '####', 'You:', 'Bot:', 'User:', '<|im_end|>', '<|eot_id|>', '\n'], '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-snugstable1-4-12b-1163-v2-mkmlizer
Waiting for job on chaiml-snugstable1-4-12b-1163-v2-mkmlizer to finish
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ /___/ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ║ ║
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: Downloaded to shared memory in 44.390s
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqcyli0xz, device:0
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: quantized model in 37.642s
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: Processed model ChaiML/SnugStable1.4-12b0-l1e5r7 in 82.032s
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-4-12b-1163-v2
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12b-1163-v2/special_tokens_map.json
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12b-1163-v2/config.json
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12b-1163-v2/tokenizer_config.json
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12b-1163-v2/tokenizer.json
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-4-12b-1163-v2/flywheel_model.0.safetensors
chaiml-snugstable1-4-12b-1163-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.94it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 43.86it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 41.86it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 40.85it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:07, 42.11it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 33.59it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 41.66it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 41.07it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 41.31it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 41.84it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 42.67it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:11, 25.24it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 32.35it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 33.58it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 35.49it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 37.49it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 32.11it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.31it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 38.42it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 40.01it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 33.64it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 33.92it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 40.48it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 39.78it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 39.91it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 40.23it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 25.10it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 25.82it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 32.82it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.73it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 36.09it/s] Loading 0: 47%|████▋ | 170/363 [00:04<00:05, 37.22it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 38.39it/s] Loading 0: 50%|████▉ | 180/363 [00:04<00:04, 39.91it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:05, 33.13it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 40.32it/s] Loading 0: 54%|█████▍ | 197/363 [00:05<00:04, 39.80it/s] Loading 0: 56%|█████▌ | 202/363 [00:05<00:04, 38.60it/s] Loading 0: 57%|█████▋ | 207/363 [00:05<00:03, 40.09it/s] Loading 0: 58%|█████▊ | 212/363 [00:05<00:04, 33.86it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:03, 38.02it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:04, 29.40it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 29.50it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 28.76it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.42it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.99it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 36.68it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.30it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 37.55it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.55it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 37.60it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 35.98it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 37.92it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 35.08it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 37.50it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:02, 36.11it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 38.48it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 36.25it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 35.74it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:27, 2.11it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.65it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:13, 3.90it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.34it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.96it/s] Loading 0: 90%|█████████ | 328/363 [00:15<00:03, 10.72it/s] Loading 0: 92%|█████████▏| 333/363 [00:15<00:02, 13.88it/s] Loading 0: 93%|█████████▎| 338/363 [00:16<00:01, 17.39it/s] Loading 0: 94%|█████████▍| 343/363 [00:16<00:00, 21.40it/s] Loading 0: 96%|█████████▌| 348/363 [00:16<00:00, 22.31it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 29.80it/s] Loading 0: 99%|█████████▉| 360/363 [00:16<00:00, 32.61it/s]
Job chaiml-snugstable1-4-12b-1163-v2-mkmlizer completed after 114.75s with status: succeeded
Stopping job with name chaiml-snugstable1-4-12b-1163-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-4-12b-1163-v2
Waiting for inference service chaiml-snugstable1-4-12b-1163-v2 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
Inference service chaiml-snugstable1-4-12b-1163-v2 ready after 270.9875376224518s
Pipeline stage MKMLDeployer completed in 271.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.958986759185791s
Received healthy response to inference request in 1.6404993534088135s
Received healthy response to inference request in 1.7313733100891113s
Received healthy response to inference request in 1.4393398761749268s
Received healthy response to inference request in 1.7838068008422852s
5 requests
0 failed requests
5th percentile: 1.479571771621704
10th percentile: 1.5198036670684814
20th percentile: 1.6002674579620362
30th percentile: 1.658674144744873
40th percentile: 1.6950237274169921
50th percentile: 1.7313733100891113
60th percentile: 1.7523467063903808
70th percentile: 1.7733201026916503
80th percentile: 1.8188427925109865
90th percentile: 1.8889147758483886
95th percentile: 1.9239507675170897
99th percentile: 1.9519795608520507
mean time: 1.7108012199401856
Pipeline stage StressChecker completed in 10.03s
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 0.73s
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 0.75s
Shutdown handler de-registered
chaiml-snugstable1-4-12b_1163_v2 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 2454.00s
Shutdown handler de-registered
chaiml-snugstable1-4-12b_1163_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-4-12b_1163_v2 status is now torndown due to DeploymentManager action
chaiml-snugstable1-4-12b_1163_v2 status is now torndown due to DeploymentManager action
chaiml-snugstable1-4-12b_1163_v2 status is now torndown due to DeploymentManager action