developer_uid: zonemercy
submission_id: chaiml-snugstable2-12b0_60240_v4
model_name: tempv1-4
model_group: ChaiML/SnugStable2-12b0-
status: torndown
timestamp: 2025-01-08T09:22:31+00:00
num_battles: 8112
num_wins: 4296
celo_rating: 1289.52
family_friendly_score: 0.5948
family_friendly_standard_error: 0.006942808653563772
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': 0.6466072858474936, 'latency_mean': 1.5464601743221282, 'latency_p50': 1.550879955291748, 'latency_p90': 1.7120558738708496}, {'batch_size': 3, 'throughput': 1.2433639167867716, 'latency_mean': 2.408151825666428, 'latency_p50': 2.4167150259017944, 'latency_p90': 2.6469321727752684}, {'batch_size': 5, 'throughput': 1.5318871224336286, 'latency_mean': 3.24893669962883, 'latency_p50': 3.2173521518707275, 'latency_p90': 3.6133166551589966}, {'batch_size': 6, 'throughput': 1.632421288912586, 'latency_mean': 3.66204603433609, 'latency_p50': 3.6611539125442505, 'latency_p90': 4.122154951095581}, {'batch_size': 8, 'throughput': 1.7149971628033667, 'latency_mean': 4.626354510784149, 'latency_p50': 4.658545017242432, 'latency_p90': 5.165021586418152}, {'batch_size': 10, 'throughput': 1.7710000747616943, 'latency_mean': 5.606090451478958, 'latency_p50': 5.606099605560303, 'latency_p90': 6.343082332611084}]
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: 1.64
us_pacific_date: 2025-01-08
win_ratio: 0.5295857988165681
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|>', '</s>', 'You:', 'Bot:', '<|im_end|>', 'User:', '\n', '####'], '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-v4-mkmlizer
Waiting for job on chaiml-snugstable2-12b0-60240-v4-mkmlizer to finish
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ /___/ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ belonging to: ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ║ ║
chaiml-snugstable2-12b0-60240-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable2-12b0-60240-v4-mkmlizer: Downloaded to shared memory in 35.434s
chaiml-snugstable2-12b0-60240-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8hksfltx, device:0
chaiml-snugstable2-12b0-60240-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable2-12b0-60240-v4-mkmlizer: quantized model in 38.705s
chaiml-snugstable2-12b0-60240-v4-mkmlizer: Processed model ChaiML/SnugStable2-12b0-l1e5r7b4 in 74.139s
chaiml-snugstable2-12b0-60240-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable2-12b0-60240-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable2-12b0-60240-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v4
chaiml-snugstable2-12b0-60240-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v4/config.json
chaiml-snugstable2-12b0-60240-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v4/special_tokens_map.json
chaiml-snugstable2-12b0-60240-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v4/tokenizer_config.json
chaiml-snugstable2-12b0-60240-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v4/tokenizer.json
chaiml-snugstable2-12b0-60240-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable2-12b0-60240-v4/flywheel_model.0.safetensors
chaiml-snugstable2-12b0-60240-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 25.70it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 41.97it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 40.83it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 40.24it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 41.83it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 33.35it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 41.40it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 40.57it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 39.63it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 39.18it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 38.85it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:11, 26.04it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:10, 27.72it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 29.57it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 29.19it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 32.33it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 31.28it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:08, 34.14it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:08, 32.75it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 34.93it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 33.16it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 32.86it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 37.08it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:07, 34.85it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 32.58it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 35.42it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 33.60it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 35.94it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 34.25it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:09, 24.35it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 24.17it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.33it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 32.19it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 31.63it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.64it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:05, 33.52it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 36.14it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 34.32it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:05, 35.90it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:05, 33.85it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 36.20it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 34.06it/s] Loading 0: 55%|█████▌ | 200/363 [00:05<00:04, 35.45it/s] Loading 0: 56%|█████▌ | 204/363 [00:06<00:05, 31.30it/s] Loading 0: 57%|█████▋ | 208/363 [00:06<00:04, 33.39it/s] Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 31.43it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 36.01it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 27.20it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.04it/s] Loading 0: 64%|██████▎ | 231/363 [00:07<00:05, 25.66it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 28.30it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 27.94it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 35.55it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 34.33it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 36.84it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.43it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 38.16it/s] Loading 0: 74%|███████▍ | 268/363 [00:08<00:02, 36.19it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 37.99it/s] Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 35.98it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 38.05it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 35.90it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 38.10it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 36.45it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 36.08it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:28, 2.11it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.63it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:13, 3.88it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:06, 6.31it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:05, 7.83it/s] Loading 0: 90%|█████████ | 327/363 [00:16<00:03, 9.84it/s] Loading 0: 91%|█████████ | 331/363 [00:16<00:02, 12.03it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:01, 16.94it/s] Loading 0: 94%|█████████▍| 342/363 [00:16<00:01, 20.24it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 23.17it/s] Loading 0: 96%|█████████▋| 350/363 [00:16<00:00, 25.29it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 30.00it/s] Loading 0: 99%|█████████▉| 360/363 [00:17<00:00, 32.77it/s]
Job chaiml-snugstable2-12b0-60240-v4-mkmlizer completed after 124.52s with status: succeeded
Stopping job with name chaiml-snugstable2-12b0-60240-v4-mkmlizer
Pipeline stage MKMLizer completed in 125.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable2-12b0-60240-v4
Waiting for inference service chaiml-snugstable2-12b0-60240-v4 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v257: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v257-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-snugstable2-12b0-60240-v4 ready after 371.6817443370819s
Pipeline stage MKMLDeployer completed in 372.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.883723258972168s
Received healthy response to inference request in 1.703120470046997s
Received healthy response to inference request in 1.4110345840454102s
Received healthy response to inference request in 1.9270505905151367s
Failed to get response for submission mistralai-mistral-nem_93303_v257: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v257-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.2924563884735107s
5 requests
0 failed requests
5th percentile: 1.4694517612457276
10th percentile: 1.5278689384460449
20th percentile: 1.6447032928466796
30th percentile: 1.7392410278320312
40th percentile: 1.8114821434020996
50th percentile: 1.883723258972168
60th percentile: 1.9010541915893555
70th percentile: 1.918385124206543
80th percentile: 2.0001317501068114
90th percentile: 2.1462940692901613
95th percentile: 2.219375228881836
99th percentile: 2.277840156555176
mean time: 1.8434770584106446
Pipeline stage StressChecker completed in 10.61s
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 0.74s
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 0.72s
Shutdown handler de-registered
chaiml-snugstable2-12b0_60240_v4 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 0.11s
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-snugstable2-12b0-60240-v4-profiler
Waiting for inference service chaiml-snugstable2-12b0-60240-v4-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 2413.83s
Shutdown handler de-registered
chaiml-snugstable2-12b0_60240_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable2-12b0_60240_v4 status is now torndown due to DeploymentManager action