developer_uid: zonemercy
submission_id: chaiml-lexens-v1-12b01e5r256_v11
model_name: tempv1-0
model_group: ChaiML/LexEns-v1-12b01e5
status: inactive
timestamp: 2024-12-18T12:51:22+00:00
num_battles: 13390
num_wins: 6957
celo_rating: 1270.48
family_friendly_score: 0.6068
family_friendly_standard_error: 0.006907876084586347
submission_type: basic
model_repo: ChaiML/LexEns-v1-12b01e5r256
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6375657195836799, 'latency_mean': 1.5683805918693543, 'latency_p50': 1.5710363388061523, 'latency_p90': 1.7322466135025023}, {'batch_size': 3, 'throughput': 1.2714887336521616, 'latency_mean': 2.3530550622940063, 'latency_p50': 2.3524796962738037, 'latency_p90': 2.58069052696228}, {'batch_size': 5, 'throughput': 1.6242081796634387, 'latency_mean': 3.0719333016872405, 'latency_p50': 3.068198084831238, 'latency_p90': 3.417687630653381}, {'batch_size': 6, 'throughput': 1.7356080509741842, 'latency_mean': 3.4338851416110994, 'latency_p50': 3.437395215034485, 'latency_p90': 3.8326892137527464}, {'batch_size': 8, 'throughput': 1.8915754308492672, 'latency_mean': 4.203191100358963, 'latency_p50': 4.215448498725891, 'latency_p90': 4.772363662719727}, {'batch_size': 10, 'throughput': 1.9733889578531703, 'latency_mean': 5.029582058191299, 'latency_p50': 5.015717148780823, 'latency_p90': 5.619931077957153}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-0
is_internal_developer: True
language_model: ChaiML/LexEns-v1-12b01e5r256
model_size: 13B
ranking_group: single
throughput_3p7s: 1.81
us_pacific_date: 2024-12-18
win_ratio: 0.5195668409260642
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': 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-lexens-v1-12b01e5r256-v11-mkmlizer
Waiting for job on chaiml-lexens-v1-12b01e5r256-v11-mkmlizer to finish
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ _____ __ __ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ /___/ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ Version: 0.11.12 ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ https://mk1.ai ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ belonging to: ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ Chai Research Corp. ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ║ ║
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: Downloaded to shared memory in 33.803s
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcn8tszby, device:0
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: quantized model in 36.700s
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: Processed model ChaiML/LexEns-v1-12b01e5r256 in 70.503s
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v11
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v11/config.json
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v11/special_tokens_map.json
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v11/tokenizer_config.json
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v11/tokenizer.json
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v11/flywheel_model.0.safetensors
chaiml-lexens-v1-12b01e5r256-v11-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.96it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.03it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.52it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 40.55it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:07, 45.32it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:07, 45.48it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 46.05it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:07, 45.33it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:08, 36.28it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:07, 41.71it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 30.94it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 30.25it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 37.00it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 38.22it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 38.52it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 43.54it/s] Loading 0: 26%|██▌ | 95/363 [00:02<00:06, 44.23it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:07, 36.61it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 45.78it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 41.33it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:06, 40.36it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 44.73it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 45.52it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:06, 36.13it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:07, 29.61it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 30.83it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.01it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:05, 38.20it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 39.06it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 40.15it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.15it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.16it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.92it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.46it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 46.43it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 37.84it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 45.64it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 45.30it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 46.02it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 28.89it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.46it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:03, 38.26it/s] Loading 0: 67%|██████▋ | 243/363 [00:06<00:02, 40.44it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 35.31it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 43.00it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 41.56it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 39.82it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 44.10it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 43.69it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 43.84it/s] Loading 0: 80%|███████▉ | 289/363 [00:07<00:01, 42.38it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 40.94it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 42.86it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:24, 2.43it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:17, 3.15it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.12it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.91it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.38it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.93it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.67it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 20.31it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.50it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.85it/s] Loading 0: 99%|█████████▉| 361/363 [00:15<00:00, 32.88it/s]
Job chaiml-lexens-v1-12b01e5r256-v11-mkmlizer completed after 95.17s with status: succeeded
Stopping job with name chaiml-lexens-v1-12b01e5r256-v11-mkmlizer
Pipeline stage MKMLizer completed in 95.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-lexens-v1-12b01e5r256-v11
Waiting for inference service chaiml-lexens-v1-12b01e5r256-v11 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-lexens-v1-12b01e5r256-v11 ready after 241.0173282623291s
Pipeline stage MKMLDeployer completed in 241.61s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8433880805969238s
Received healthy response to inference request in 1.3978285789489746s
Received healthy response to inference request in 1.425100564956665s
Received healthy response to inference request in 1.4012553691864014s
Received healthy response to inference request in 1.7825639247894287s
5 requests
0 failed requests
5th percentile: 1.3985139369964599
10th percentile: 1.3991992950439454
20th percentile: 1.400570011138916
30th percentile: 1.406024408340454
40th percentile: 1.4155624866485597
50th percentile: 1.425100564956665
60th percentile: 1.5680859088897705
70th percentile: 1.711071252822876
80th percentile: 1.7947287559509277
90th percentile: 1.8190584182739258
95th percentile: 1.8312232494354248
99th percentile: 1.8409551143646241
mean time: 1.5700273036956787
Pipeline stage StressChecker completed in 9.18s
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 2.54s
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 2.27s
Shutdown handler de-registered
chaiml-lexens-v1-12b01e5r256_v11 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-lexens-v1-12b01e5r256-v11-profiler
Waiting for inference service chaiml-lexens-v1-12b01e5r256-v11-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 3029.84s
Shutdown handler de-registered
chaiml-lexens-v1-12b01e5r256_v11 status is now inactive due to auto deactivation removed underperforming models