developer_uid: zonemercy
submission_id: chaiml-nemo-anthropic-ad_3823_v7
model_name: chaiml-nemo-anthropic-ad_3823_v7
model_group: ChaiML/nemo_anthropic_ad
status: inactive
timestamp: 2024-12-03T12:10:30+00:00
num_battles: 15365
num_wins: 7784
celo_rating: 1267.92
family_friendly_score: 0.5813999999999999
family_friendly_standard_error: 0.006976733333014814
submission_type: basic
model_repo: ChaiML/nemo_anthropic_addict_lexical_1120_run2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6348458102207991, 'latency_mean': 1.5750917637348174, 'latency_p50': 1.5703338384628296, 'latency_p90': 1.7298520088195801}, {'batch_size': 3, 'throughput': 1.2546160406858584, 'latency_mean': 2.381552221775055, 'latency_p50': 2.3788739442825317, 'latency_p90': 2.61490638256073}, {'batch_size': 5, 'throughput': 1.590787105010784, 'latency_mean': 3.130250587463379, 'latency_p50': 3.1443793773651123, 'latency_p90': 3.4870628118515015}, {'batch_size': 6, 'throughput': 1.7061338712436955, 'latency_mean': 3.492482680082321, 'latency_p50': 3.471342921257019, 'latency_p90': 3.954162049293518}, {'batch_size': 8, 'throughput': 1.8445145872575581, 'latency_mean': 4.309826784133911, 'latency_p50': 4.322673201560974, 'latency_p90': 4.924888014793396}, {'batch_size': 10, 'throughput': 1.931965082847105, 'latency_mean': 5.137943742275238, 'latency_p50': 5.107351183891296, 'latency_p90': 5.771338129043579}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-anthropic-ad_3823_v7
is_internal_developer: True
language_model: ChaiML/nemo_anthropic_addict_lexical_1120_run2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.76
us_pacific_date: 2024-12-03
win_ratio: 0.5066059225512528
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', '<|eot_id|>', '<|end_of_text|>', 'You:'], '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': '### Response:\n{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-nemo-anthropic-ad-3823-v7-mkmlizer
Waiting for job on chaiml-nemo-anthropic-ad-3823-v7-mkmlizer to finish
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ /___/ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ belonging to: ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: Downloaded to shared memory in 34.332s
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5dbc9dxt, device:0
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission function_lijit_2024-11-26: ('http://chaiml-llama-8b-multihea-7810-v3-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41036->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: quantized model in 38.375s
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: Processed model ChaiML/nemo_anthropic_addict_lexical_1120_run2 in 72.708s
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v7
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v7/config.json
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v7/special_tokens_map.json
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v7/tokenizer_config.json
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v7/tokenizer.json
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v7/flywheel_model.0.safetensors
chaiml-nemo-anthropic-ad-3823-v7-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.53it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 42.21it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 39.74it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 39.10it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 40.94it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 35.28it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 44.86it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:07, 43.60it/s] Loading 0: 14%|█▍ | 51/363 [00:01<00:07, 41.32it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:07, 40.95it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:10, 29.37it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 29.59it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 35.83it/s] Loading 0: 21%|██ | 76/363 [00:02<00:07, 37.92it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 40.26it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 42.42it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 36.18it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 43.67it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 42.97it/s] Loading 0: 30%|███ | 109/363 [00:02<00:05, 46.80it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:06, 37.01it/s] Loading 0: 33%|███▎ | 119/363 [00:03<00:07, 34.58it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 39.37it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:06, 37.50it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:06, 37.84it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 37.99it/s] Loading 0: 39%|███▉ | 143/363 [00:03<00:08, 25.05it/s] Loading 0: 40%|████ | 147/363 [00:04<00:08, 26.18it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:07, 27.42it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 31.43it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 31.39it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 34.53it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 33.49it/s] Loading 0: 48%|████▊ | 173/363 [00:04<00:05, 35.04it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:05, 31.11it/s] Loading 0: 50%|████▉ | 181/363 [00:05<00:05, 32.80it/s] Loading 0: 51%|█████ | 185/363 [00:05<00:05, 30.26it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 38.18it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 36.18it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 38.63it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 36.57it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 38.58it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:04, 35.63it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 34.39it/s] Loading 0: 61%|██████ | 222/363 [00:06<00:03, 35.80it/s] Loading 0: 62%|██████▏ | 226/363 [00:06<00:05, 23.16it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:05, 24.24it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 32.61it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 32.86it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 35.57it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 32.81it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:03, 34.54it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:03, 33.00it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 35.35it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 34.39it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 36.51it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 35.53it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 38.35it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 36.77it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 38.61it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 36.80it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 36.37it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:27, 2.12it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.66it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:12, 3.93it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:06, 6.73it/s] Loading 0: 90%|████████▉ | 326/363 [00:15<00:04, 9.21it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:02, 11.68it/s] Loading 0: 93%|█████████▎| 338/363 [00:16<00:01, 16.42it/s] Loading 0: 94%|█████████▍| 343/363 [00:16<00:01, 19.99it/s] Loading 0: 96%|█████████▌| 348/363 [00:16<00:00, 21.37it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 27.73it/s] Loading 0: 99%|█████████▉| 360/363 [00:16<00:00, 29.47it/s]
Job chaiml-nemo-anthropic-ad-3823-v7-mkmlizer completed after 104.41s with status: succeeded
Stopping job with name chaiml-nemo-anthropic-ad-3823-v7-mkmlizer
Pipeline stage MKMLizer completed in 104.90s
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-nemo-anthropic-ad-3823-v7
Waiting for inference service chaiml-nemo-anthropic-ad-3823-v7 to be ready
Inference service chaiml-nemo-anthropic-ad-3823-v7 ready after 151.33817529678345s
Pipeline stage MKMLDeployer completed in 151.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7924511432647705s
Received healthy response to inference request in 1.5984363555908203s
Received healthy response to inference request in 1.5999643802642822s
Received healthy response to inference request in 1.9539928436279297s
Received healthy response to inference request in 2.5659916400909424s
5 requests
0 failed requests
5th percentile: 1.5987419605255127
10th percentile: 1.599047565460205
20th percentile: 1.5996587753295899
30th percentile: 1.6384617328643798
40th percentile: 1.7154564380645752
50th percentile: 1.7924511432647705
60th percentile: 1.8570678234100342
70th percentile: 1.9216845035552979
80th percentile: 2.0763926029205324
90th percentile: 2.3211921215057374
95th percentile: 2.4435918807983397
99th percentile: 2.541511688232422
mean time: 1.902167272567749
Pipeline stage StressChecker completed in 10.89s
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 2.18s
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 2.09s
Shutdown handler de-registered
chaiml-nemo-anthropic-ad_3823_v7 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-nemo-anthropic-ad-3823-v7-profiler
Waiting for inference service chaiml-nemo-anthropic-ad-3823-v7-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 2801.16s
Shutdown handler de-registered
chaiml-nemo-anthropic-ad_3823_v7 status is now inactive due to auto deactivation removed underperforming models