developer_uid: zonemercy
submission_id: chaiml-snugstable1-12b0-_4307_v1
model_name: tempv1-1
model_group: ChaiML/SnugStable1-12b0-
status: torndown
timestamp: 2024-12-26T10:30:51+00:00
num_battles: 20590
num_wins: 11402
celo_rating: 1303.79
family_friendly_score: 0.5528
family_friendly_standard_error: 0.007031531269929758
submission_type: basic
model_repo: ChaiML/SnugStable1-12b0-1e5r128
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': 0.6347891036555754, 'latency_mean': 1.5752481091022492, 'latency_p50': 1.5824406147003174, 'latency_p90': 1.7306314468383788}, {'batch_size': 3, 'throughput': 1.2573519084589808, 'latency_mean': 2.3827065443992614, 'latency_p50': 2.3748773336410522, 'latency_p90': 2.6118472099304197}, {'batch_size': 5, 'throughput': 1.5866263823660205, 'latency_mean': 3.1367258727550507, 'latency_p50': 3.1393582820892334, 'latency_p90': 3.486984395980835}, {'batch_size': 6, 'throughput': 1.709688925855277, 'latency_mean': 3.4903009259700775, 'latency_p50': 3.4810749292373657, 'latency_p90': 3.974973940849304}, {'batch_size': 8, 'throughput': 1.8503588481978681, 'latency_mean': 4.283239018917084, 'latency_p50': 4.31365704536438, 'latency_p90': 4.805195260047912}, {'batch_size': 10, 'throughput': 1.9128410036996402, 'latency_mean': 5.202608516216278, 'latency_p50': 5.187845230102539, 'latency_p90': 5.958781790733338}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-1
is_internal_developer: True
language_model: ChaiML/SnugStable1-12b0-1e5r128
model_size: 13B
ranking_group: single
throughput_3p7s: 1.76
us_pacific_date: 2024-12-26
win_ratio: 0.5537639630888781
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:', 'You:', '<|im_end|>', '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-snugstable1-12b0-4307-v1-mkmlizer
Waiting for job on chaiml-snugstable1-12b0-4307-v1-mkmlizer to finish
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ /___/ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ║ ║
chaiml-snugstable1-12b0-4307-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-snugstable1-12b0-4307-v1-mkmlizer: Downloaded to shared memory in 49.281s
chaiml-snugstable1-12b0-4307-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgc2haty3, device:0
chaiml-snugstable1-12b0-4307-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-12b0-4307-v1-mkmlizer: quantized model in 38.915s
chaiml-snugstable1-12b0-4307-v1-mkmlizer: Processed model ChaiML/SnugStable1-12b0-1e5r128 in 88.196s
chaiml-snugstable1-12b0-4307-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-12b0-4307-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-12b0-4307-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-12b0-4307-v1
chaiml-snugstable1-12b0-4307-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-12b0-4307-v1/config.json
chaiml-snugstable1-12b0-4307-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-12b0-4307-v1/special_tokens_map.json
chaiml-snugstable1-12b0-4307-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-12b0-4307-v1/tokenizer_config.json
chaiml-snugstable1-12b0-4307-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-12b0-4307-v1/tokenizer.json
chaiml-snugstable1-12b0-4307-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-12b0-4307-v1/flywheel_model.0.safetensors
chaiml-snugstable1-12b0-4307-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 25.37it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 42.04it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 39.66it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 38.13it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 36.34it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:09, 35.82it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 34.13it/s] Loading 0: 10%|█ | 38/363 [00:01<00:09, 35.35it/s] Loading 0: 12%|█▏ | 42/363 [00:01<00:10, 31.14it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 37.12it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:08, 35.52it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:08, 35.60it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:10, 27.79it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 27.27it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:08, 34.12it/s] Loading 0: 21%|██ | 75/363 [00:02<00:08, 35.26it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 40.02it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 42.06it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 34.49it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 41.05it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 40.23it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 41.45it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 34.48it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 34.07it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 40.49it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 39.67it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 39.10it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 40.56it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 25.83it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 26.30it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:05, 34.56it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 35.70it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 37.62it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 39.02it/s] Loading 0: 48%|████▊ | 176/363 [00:05<00:05, 31.50it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 38.12it/s] Loading 0: 52%|█████▏ | 188/363 [00:05<00:04, 37.87it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:04, 38.15it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:04, 38.92it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:05, 31.73it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:04, 37.95it/s] Loading 0: 59%|█████▉ | 215/363 [00:06<00:04, 36.93it/s] Loading 0: 60%|██████ | 219/363 [00:06<00:03, 36.69it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 26.12it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 27.32it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:05, 25.13it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:04, 30.78it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 31.11it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 34.86it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 33.91it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 36.71it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.13it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 38.62it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 38.76it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 39.42it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:02, 40.19it/s] Loading 0: 78%|███████▊ | 284/363 [00:08<00:02, 33.20it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 39.96it/s] Loading 0: 82%|████████▏ | 296/363 [00:08<00:01, 38.91it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 40.42it/s] Loading 0: 84%|████████▍ | 306/363 [00:15<00:23, 2.40it/s] Loading 0: 85%|████████▌ | 309/363 [00:15<00:18, 2.93it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:14, 3.61it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:07, 6.02it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.57it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.22it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:02, 12.39it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:01, 16.14it/s] Loading 0: 94%|█████████▍| 341/363 [00:16<00:01, 18.43it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 22.47it/s] Loading 0: 96%|█████████▋| 350/363 [00:16<00:00, 24.19it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 28.32it/s] Loading 0: 99%|█████████▉| 359/363 [00:16<00:00, 28.89it/s]
Job chaiml-snugstable1-12b0-4307-v1-mkmlizer completed after 114.37s with status: succeeded
Stopping job with name chaiml-snugstable1-12b0-4307-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.84s
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-snugstable1-12b0-4307-v1
Waiting for inference service chaiml-snugstable1-12b0-4307-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-snugstable1-12b0-4307-v1 ready after 281.4503221511841s
Pipeline stage MKMLDeployer completed in 281.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6631340980529785s
Received healthy response to inference request in 1.3729588985443115s
Received healthy response to inference request in 1.4081978797912598s
Received healthy response to inference request in 1.5877892971038818s
Received healthy response to inference request in 1.3365907669067383s
5 requests
0 failed requests
5th percentile: 1.3438643932342529
10th percentile: 1.3511380195617675
20th percentile: 1.365685272216797
30th percentile: 1.380006694793701
40th percentile: 1.3941022872924804
50th percentile: 1.4081978797912598
60th percentile: 1.4800344467163087
70th percentile: 1.5518710136413574
80th percentile: 1.6028582572937011
90th percentile: 1.63299617767334
95th percentile: 1.6480651378631592
99th percentile: 1.6601203060150147
mean time: 1.473734188079834
Pipeline stage StressChecker completed in 9.28s
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 0.68s
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-snugstable1-12b0-_4307_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-snugstable1-12b0-4307-v1-profiler
Waiting for inference service chaiml-snugstable1-12b0-4307-v1-profiler to be ready
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 2637.11s
Shutdown handler de-registered
chaiml-snugstable1-12b0-_4307_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-12b0-_4307_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable1-12b0-_4307_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable1-12b0-_4307_v1 status is now torndown due to DeploymentManager action