developer_uid: rirv938
submission_id: chaiml-snugstable1-5-1_59274_v24
model_name: chaiml-snugstable1-5-1_59274_v24
model_group: ChaiML/SnugStable1.5-12b
status: torndown
timestamp: 2025-03-18T19:04:00+00:00
num_battles: 9265
num_wins: 4493
celo_rating: 1266.47
family_friendly_score: 0.48919999999999997
family_friendly_standard_error: 0.007069418080719233
submission_type: basic
model_repo: ChaiML/SnugStable1.5-12b0-l1e5r7
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6149135528000905, 'latency_mean': 1.6261719036102296, 'latency_p50': 1.6136778593063354, 'latency_p90': 1.800803804397583}, {'batch_size': 3, 'throughput': 1.1342151288009934, 'latency_mean': 2.6440982580184937, 'latency_p50': 2.6456722021102905, 'latency_p90': 2.8826440811157226}, {'batch_size': 5, 'throughput': 1.3647435615356276, 'latency_mean': 3.647885849475861, 'latency_p50': 3.614743232727051, 'latency_p90': 4.057237195968628}, {'batch_size': 6, 'throughput': 1.4419976872260423, 'latency_mean': 4.130623779296875, 'latency_p50': 4.137030720710754, 'latency_p90': 4.667528700828552}, {'batch_size': 8, 'throughput': 1.5177983159894834, 'latency_mean': 5.230964992046356, 'latency_p50': 5.223757863044739, 'latency_p90': 5.892183184623718}, {'batch_size': 10, 'throughput': 1.546381781897571, 'latency_mean': 6.405460523366928, 'latency_p50': 6.428549289703369, 'latency_p90': 7.208989000320434}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-snugstable1-5-1_59274_v24
is_internal_developer: True
language_model: ChaiML/SnugStable1.5-12b0-l1e5r7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2025-03-18
win_ratio: 0.48494333513221805
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': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, '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-snugstable1-5-1-59274-v24-mkmlizer
Waiting for job on chaiml-snugstable1-5-1-59274-v24-mkmlizer to finish
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ _____ __ __ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ /___/ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ Version: 0.12.8 ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ https://mk1.ai ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ belonging to: ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ Chai Research Corp. ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ║ ║
chaiml-snugstable1-5-1-59274-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-5-1-59274-v24-mkmlizer: Downloaded to shared memory in 28.429s
chaiml-snugstable1-5-1-59274-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpudu2fp8o, device:0
chaiml-snugstable1-5-1-59274-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-1-59274-v24-mkmlizer: quantized model in 34.828s
chaiml-snugstable1-5-1-59274-v24-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7 in 63.257s
chaiml-snugstable1-5-1-59274-v24-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-1-59274-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-1-59274-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-1-59274-v24
chaiml-snugstable1-5-1-59274-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-1-59274-v24/config.json
chaiml-snugstable1-5-1-59274-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-1-59274-v24/special_tokens_map.json
chaiml-snugstable1-5-1-59274-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-1-59274-v24/tokenizer_config.json
chaiml-snugstable1-5-1-59274-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-1-59274-v24/tokenizer.json
chaiml-snugstable1-5-1-59274-v24-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.88it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.34it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 49.61it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 51.10it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 53.84it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 51.24it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 51.09it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 52.99it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 50.47it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:07, 37.85it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.79it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 42.59it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 43.98it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 44.51it/s] Loading 0: 25%|██▍ | 90/363 [00:01<00:05, 49.76it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 48.43it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 47.17it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 55.54it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 50.07it/s] Loading 0: 33%|███▎ | 121/363 [00:02<00:05, 48.19it/s] Loading 0: 35%|███▍ | 127/363 [00:02<00:05, 44.19it/s] Loading 0: 37%|███▋ | 135/363 [00:02<00:04, 51.75it/s] Loading 0: 39%|███▉ | 141/363 [00:02<00:04, 50.57it/s] Loading 0: 40%|████ | 147/363 [00:03<00:06, 35.94it/s] Loading 0: 42%|████▏ | 152/363 [00:03<00:05, 38.01it/s] Loading 0: 44%|████▎ | 158/363 [00:03<00:05, 37.47it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 45.81it/s] Loading 0: 47%|████▋ | 172/363 [00:03<00:04, 45.43it/s] Loading 0: 49%|████▉ | 177/363 [00:03<00:04, 45.21it/s] Loading 0: 51%|█████ | 184/363 [00:03<00:03, 49.49it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:03, 48.34it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:03, 49.03it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 50.28it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 48.24it/s] Loading 0: 59%|█████▊ | 213/363 [00:04<00:03, 47.66it/s] Loading 0: 61%|██████ | 220/363 [00:04<00:02, 53.50it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 33.60it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 34.72it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 40.54it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 41.48it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 41.78it/s] Loading 0: 71%|███████ | 256/363 [00:05<00:02, 46.81it/s] Loading 0: 72%|███████▏ | 262/363 [00:05<00:02, 46.34it/s] Loading 0: 74%|███████▎ | 267/363 [00:05<00:02, 45.00it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 49.20it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 47.87it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 46.15it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 49.94it/s] Loading 0: 82%|████████▏ | 298/363 [00:06<00:01, 48.02it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:20, 2.87it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:15, 3.59it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:11, 4.58it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:05, 7.41it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:03, 9.94it/s] Loading 0: 91%|█████████ | 331/363 [00:13<00:02, 12.53it/s] Loading 0: 93%|█████████▎| 338/363 [00:13<00:01, 17.47it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 21.13it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 24.55it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 31.15it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 33.88it/s]
Job chaiml-snugstable1-5-1-59274-v24-mkmlizer completed after 93.85s with status: succeeded
Stopping job with name chaiml-snugstable1-5-1-59274-v24-mkmlizer
Pipeline stage MKMLizer completed in 94.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-5-1-59274-v24
Waiting for inference service chaiml-snugstable1-5-1-59274-v24 to be ready
Inference service chaiml-snugstable1-5-1-59274-v24 ready after 90.5196282863617s
Pipeline stage MKMLDeployer completed in 91.11s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.18741512298584s
Received healthy response to inference request in 1.6023664474487305s
Received healthy response to inference request in 1.7643287181854248s
Received healthy response to inference request in 1.6580250263214111s
5 requests
1 failed requests
5th percentile: 1.6134981632232666
10th percentile: 1.6246298789978026
20th percentile: 1.646893310546875
30th percentile: 1.6792857646942139
40th percentile: 1.7218072414398193
50th percentile: 1.7643287181854248
60th percentile: 1.9335632801055909
70th percentile: 2.102797842025757
80th percentile: 5.7745735645294225
90th percentile: 12.948890447616579
95th percentile: 16.536048889160153
99th percentile: 19.405775642395017
mean time: 5.467068529129028
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7328517436981201s
Received healthy response to inference request in 1.7100224494934082s
Received healthy response to inference request in 1.5501749515533447s
Received healthy response to inference request in 1.811250925064087s
Received healthy response to inference request in 1.747054100036621s
5 requests
0 failed requests
5th percentile: 1.5821444511413574
10th percentile: 1.61411395072937
20th percentile: 1.6780529499053956
30th percentile: 1.7145883083343505
40th percentile: 1.7237200260162353
50th percentile: 1.7328517436981201
60th percentile: 1.7385326862335204
70th percentile: 1.744213628768921
80th percentile: 1.7598934650421143
90th percentile: 1.7855721950531005
95th percentile: 1.7984115600585937
99th percentile: 1.8086830520629882
mean time: 1.7102708339691162
Pipeline stage StressChecker completed in 38.70s
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 0.71s
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 0.73s
Shutdown handler de-registered
chaiml-snugstable1-5-1_59274_v24 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4541.42s
Shutdown handler de-registered
chaiml-snugstable1-5-1_59274_v24 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-1_59274_v24 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1