developer_uid: zonemercy
submission_id: chaiml-snugstable2-12b0_60240_v1
model_name: tempv1-4
model_group: ChaiML/SnugStable2-12b0-
status: torndown
timestamp: 2025-01-07T06:46:10+00:00
num_battles: 8754
num_wins: 4556
celo_rating: 1284.63
family_friendly_score: 0.5933999999999999
family_friendly_standard_error: 0.006946602622865367
submission_type: basic
model_repo: ChaiML/SnugStable2-12b0-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': 0.6544225938287114, 'latency_mean': 1.5279703652858734, 'latency_p50': 1.5220468044281006, 'latency_p90': 1.702516222000122}, {'batch_size': 3, 'throughput': 1.2563063283397384, 'latency_mean': 2.3828742718696594, 'latency_p50': 2.3686680793762207, 'latency_p90': 2.6068686485290526}, {'batch_size': 5, 'throughput': 1.5390218709465546, 'latency_mean': 3.226467173099518, 'latency_p50': 3.2495484352111816, 'latency_p90': 3.637462615966797}, {'batch_size': 6, 'throughput': 1.65071713216707, 'latency_mean': 3.609147547483444, 'latency_p50': 3.604751229286194, 'latency_p90': 4.039704966545105}, {'batch_size': 8, 'throughput': 1.7482062735303665, 'latency_mean': 4.547218257188797, 'latency_p50': 4.534183621406555, 'latency_p90': 5.070620083808899}, {'batch_size': 10, 'throughput': 1.7772826305022278, 'latency_mean': 5.581033560037613, 'latency_p50': 5.620864510536194, 'latency_p90': 6.203391265869141}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-4
is_internal_developer: True
language_model: ChaiML/SnugStable2-12b0-l1e5r7b4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.67
us_pacific_date: 2025-01-06
win_ratio: 0.5204477952935801
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|>', '####', 'User:', '\n', '</s>', 'You:', 'Bot:', '<|im_end|>'], '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-snugstable2-12b0-60240-v1-mkmlizer
Waiting for job on chaiml-snugstable2-12b0-60240-v1-mkmlizer to finish
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ /___/ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ belonging to: ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable2-12b0-60240-v1-mkmlizer: Downloaded to shared memory in 47.393s
chaiml-snugstable2-12b0-60240-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuszkg5pv, device:0
chaiml-snugstable2-12b0-60240-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable2-12b0-60240-v1-mkmlizer: quantized model in 37.713s
chaiml-snugstable2-12b0-60240-v1-mkmlizer: Processed model ChaiML/SnugStable2-12b0-l1e5r7b4 in 85.106s
chaiml-snugstable2-12b0-60240-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable2-12b0-60240-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable2-12b0-60240-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v1
chaiml-snugstable2-12b0-60240-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v1/config.json
chaiml-snugstable2-12b0-60240-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v1/special_tokens_map.json
chaiml-snugstable2-12b0-60240-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v1/tokenizer_config.json
chaiml-snugstable2-12b0-60240-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v1/tokenizer.json
chaiml-snugstable2-12b0-60240-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.57it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 43.99it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 42.62it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 41.78it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:07, 43.30it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 34.11it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 41.71it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 42.20it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 42.30it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 42.96it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 44.27it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:12, 24.25it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 31.26it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 32.99it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 35.28it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 37.74it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 32.66it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 39.26it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 39.43it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 41.14it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 32.15it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 32.92it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 39.28it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 39.19it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 40.11it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 41.17it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 25.21it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 25.78it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 32.84it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.58it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 35.14it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 34.23it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:05, 36.72it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:05, 35.35it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 36.90it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:04, 35.59it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 38.19it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 35.88it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 37.85it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 36.87it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 39.81it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 39.51it/s] Loading 0: 60%|██████ | 219/363 [00:06<00:03, 39.45it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:04, 28.27it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 27.55it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 27.54it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 33.20it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 30.91it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 33.95it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 34.30it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 37.59it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 36.75it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 38.99it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 37.20it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 39.22it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 36.62it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 39.30it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 37.23it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 39.34it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 37.21it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 36.93it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:27, 2.13it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:20, 2.67it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:12, 3.94it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.40it/s] Loading 0: 89%|████████▉ | 324/363 [00:15<00:04, 8.54it/s] Loading 0: 91%|█████████ | 329/363 [00:15<00:03, 11.21it/s] Loading 0: 92%|█████████▏| 335/363 [00:15<00:01, 14.61it/s] Loading 0: 94%|█████████▎| 340/363 [00:16<00:01, 17.70it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 22.69it/s] Loading 0: 97%|█████████▋| 351/363 [00:16<00:00, 25.75it/s] Loading 0: 98%|█████████▊| 356/363 [00:16<00:00, 28.92it/s] Loading 0: 99%|█████████▉| 361/363 [00:16<00:00, 32.22it/s]
Job chaiml-snugstable2-12b0-60240-v1-mkmlizer completed after 124.2s with status: succeeded
Stopping job with name chaiml-snugstable2-12b0-60240-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.74s
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-snugstable2-12b0-60240-v1
Waiting for inference service chaiml-snugstable2-12b0-60240-v1 to be ready
Inference service chaiml-snugstable2-12b0-60240-v1 ready after 371.5078420639038s
Pipeline stage MKMLDeployer completed in 372.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9208567142486572s
Received healthy response to inference request in 1.512223482131958s
Received healthy response to inference request in 1.5486717224121094s
Received healthy response to inference request in 1.79795241355896s
Received healthy response to inference request in 1.4106409549713135s
5 requests
0 failed requests
5th percentile: 1.4309574604034423
10th percentile: 1.4512739658355713
20th percentile: 1.4919069766998292
30th percentile: 1.5195131301879883
40th percentile: 1.5340924263000488
50th percentile: 1.5486717224121094
60th percentile: 1.6483839988708495
70th percentile: 1.7480962753295899
80th percentile: 1.8225332736968993
90th percentile: 1.8716949939727783
95th percentile: 1.8962758541107179
99th percentile: 1.9159405422210694
mean time: 1.6380690574645995
Pipeline stage StressChecker completed in 9.55s
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 0.75s
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 0.65s
Shutdown handler de-registered
chaiml-snugstable2-12b0_60240_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-snugstable2-12b0-60240-v1-profiler
Waiting for inference service chaiml-snugstable2-12b0-60240-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 2526.32s
Shutdown handler de-registered
chaiml-snugstable2-12b0_60240_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable2-12b0_60240_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable2-12b0_60240_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable2-12b0_60240_v1 status is now torndown due to DeploymentManager action