developer_uid: zonemercy
submission_id: chaiml-snugstable1-4-12_11636_v4
model_name: tempv1-1
model_group: ChaiML/SnugStable1.4-12b
status: torndown
timestamp: 2025-01-02T04:08:02+00:00
num_battles: 14815
num_wins: 8059
celo_rating: 1307.28
family_friendly_score: 0.579
family_friendly_standard_error: 0.006982248921371967
submission_type: basic
model_repo: ChaiML/SnugStable1.4-12b0-l1e5r7
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': 0.6578108072663764, 'latency_mean': 1.520096687078476, 'latency_p50': 1.5131711959838867, 'latency_p90': 1.7002247333526612}, {'batch_size': 3, 'throughput': 1.2650020205389347, 'latency_mean': 2.3642635214328767, 'latency_p50': 2.3597614765167236, 'latency_p90': 2.6275763273239137}, {'batch_size': 5, 'throughput': 1.5646769685828177, 'latency_mean': 3.173506669998169, 'latency_p50': 3.1629793643951416, 'latency_p90': 3.573696827888489}, {'batch_size': 6, 'throughput': 1.6752378454636558, 'latency_mean': 3.5602399110794067, 'latency_p50': 3.5526931285858154, 'latency_p90': 3.9918118953704833}, {'batch_size': 8, 'throughput': 1.7514662821347957, 'latency_mean': 4.543118535280228, 'latency_p50': 4.579154372215271, 'latency_p90': 5.079609012603759}, {'batch_size': 10, 'throughput': 1.814360725198983, 'latency_mean': 5.476149824857711, 'latency_p50': 5.538180470466614, 'latency_p90': 6.106472969055176}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-1
is_internal_developer: True
language_model: ChaiML/SnugStable1.4-12b0-l1e5r7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.7
us_pacific_date: 2025-01-01
win_ratio: 0.5439757003037462
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': ['Bot:', '</s>', 'User:', '<|eot_id|>', '<|im_end|>', 'You:', '\n', '####'], 'max_input_tokens': 768, 'best_of': 8, '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-snugstable1-4-12-11636-v4-mkmlizer
Waiting for job on chaiml-snugstable1-4-12-11636-v4-mkmlizer to finish
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ /___/ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ Version: 0.11.12 ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ║ ║
chaiml-snugstable1-4-12-11636-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-4-12-11636-v4-mkmlizer: Downloaded to shared memory in 54.382s
chaiml-snugstable1-4-12-11636-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpooyabwlz, device:0
chaiml-snugstable1-4-12-11636-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-4-12-11636-v4-mkmlizer: quantized model in 39.922s
chaiml-snugstable1-4-12-11636-v4-mkmlizer: Processed model ChaiML/SnugStable1.4-12b0-l1e5r7 in 94.304s
chaiml-snugstable1-4-12-11636-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-4-12-11636-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-4-12-11636-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v4
chaiml-snugstable1-4-12-11636-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v4/config.json
chaiml-snugstable1-4-12-11636-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v4/special_tokens_map.json
chaiml-snugstable1-4-12-11636-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v4/tokenizer_config.json
chaiml-snugstable1-4-12-11636-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v4/tokenizer.json
chaiml-snugstable1-4-12-11636-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-4-12-11636-v4/flywheel_model.0.safetensors
chaiml-snugstable1-4-12-11636-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.16it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:10, 34.54it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:11, 29.69it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:08, 39.49it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:08, 39.29it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:08, 38.59it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:09, 35.88it/s] Loading 0: 11%|█ | 39/363 [00:01<00:09, 35.62it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:09, 34.84it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 37.93it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:08, 35.79it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:08, 36.10it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:11, 26.17it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:11, 25.68it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:10, 28.49it/s] Loading 0: 20%|██ | 73/363 [00:02<00:10, 27.75it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 35.86it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 34.53it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 36.60it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 34.71it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 36.90it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:07, 35.08it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 34.53it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 38.10it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:07, 34.88it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 33.08it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 35.47it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:07, 33.11it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 35.52it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 34.37it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:08, 24.70it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 22.48it/s] Loading 0: 41%|████ | 149/363 [00:04<00:09, 21.65it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 29.82it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 30.10it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:05, 33.49it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:05, 32.79it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 35.98it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 34.69it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 36.53it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:05, 34.11it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 36.53it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 34.30it/s] Loading 0: 55%|█████▌ | 200/363 [00:06<00:04, 35.46it/s] Loading 0: 56%|█████▌ | 204/363 [00:06<00:04, 32.10it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 37.88it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 34.97it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 35.10it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 27.13it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 28.38it/s] Loading 0: 64%|██████▎ | 231/363 [00:07<00:04, 27.65it/s] Loading 0: 65%|██████▌ | 237/363 [00:07<00:03, 33.31it/s] Loading 0: 66%|██████▋ | 241/363 [00:07<00:03, 32.36it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 35.33it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 33.96it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 36.67it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:03, 34.24it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 37.29it/s] Loading 0: 74%|███████▍ | 268/363 [00:08<00:02, 35.07it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 37.92it/s] Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 35.74it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 38.39it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 35.94it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 38.21it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 36.05it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 35.77it/s] Loading 0: 84%|████████▎ | 304/363 [00:16<00:29, 1.99it/s] Loading 0: 85%|████████▍ | 307/363 [00:16<00:22, 2.49it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:13, 3.66it/s] Loading 0: 88%|████████▊ | 319/363 [00:16<00:07, 5.96it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:05, 7.49it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.08it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:02, 12.23it/s] Loading 0: 93%|█████████▎| 337/363 [00:17<00:01, 15.92it/s] Loading 0: 94%|█████████▍| 341/363 [00:17<00:01, 18.20it/s] Loading 0: 95%|█████████▌| 346/363 [00:17<00:00, 22.40it/s] Loading 0: 96%|█████████▋| 350/363 [00:17<00:00, 24.05it/s] Loading 0: 98%|█████████▊| 355/363 [00:17<00:00, 28.25it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 28.72it/s]
Job chaiml-snugstable1-4-12-11636-v4-mkmlizer completed after 125.67s with status: succeeded
Stopping job with name chaiml-snugstable1-4-12-11636-v4-mkmlizer
Pipeline stage MKMLizer completed in 126.23s
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-snugstable1-4-12-11636-v4
Waiting for inference service chaiml-snugstable1-4-12-11636-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-snugstable1-4-12-11636-v4 ready after 341.2900815010071s
Pipeline stage MKMLDeployer completed in 341.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8250689506530762s
Received healthy response to inference request in 1.672318935394287s
Received healthy response to inference request in 1.7510085105895996s
Received healthy response to inference request in 1.606879472732544s
Received healthy response to inference request in 1.74436616897583s
5 requests
0 failed requests
5th percentile: 1.6199673652648925
10th percentile: 1.6330552577972413
20th percentile: 1.6592310428619386
30th percentile: 1.6867283821105956
40th percentile: 1.7155472755432128
50th percentile: 1.74436616897583
60th percentile: 1.747023105621338
70th percentile: 1.7496800422668457
80th percentile: 1.765820598602295
90th percentile: 1.7954447746276856
95th percentile: 1.8102568626403808
99th percentile: 1.822106533050537
mean time: 1.7199284076690673
Pipeline stage StressChecker completed in 9.92s
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 0.90s
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 0.67s
Shutdown handler de-registered
chaiml-snugstable1-4-12_11636_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 0.10s
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-snugstable1-4-12-11636-v4-profiler
Waiting for inference service chaiml-snugstable1-4-12-11636-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 2546.04s
Shutdown handler de-registered
chaiml-snugstable1-4-12_11636_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-4-12_11636_v4 status is now torndown due to DeploymentManager action
chaiml-snugstable1-4-12_11636_v4 status is now torndown due to DeploymentManager action
chaiml-snugstable1-4-12_11636_v4 status is now torndown due to DeploymentManager action