developer_uid: Jellywibble
submission_id: chaiml-nemo-anthropic-ad_3823_v5
model_name: chaiml-nemo-anthropic-ad_3823_v5
model_group: ChaiML/nemo_anthropic_ad
status: inactive
timestamp: 2024-11-30T18:07:42+00:00
num_battles: 12609
num_wins: 6568
celo_rating: 1278.78
family_friendly_score: 0.5786
family_friendly_standard_error: 0.006983151723971061
submission_type: basic
model_repo: ChaiML/nemo_anthropic_addict_lexical_1120_run2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6510240167836044, 'latency_mean': 1.5359837758541106, 'latency_p50': 1.5378155708312988, 'latency_p90': 1.7046105146408081}, {'batch_size': 3, 'throughput': 1.2455009354224846, 'latency_mean': 2.3980253660678863, 'latency_p50': 2.3999096155166626, 'latency_p90': 2.671557903289795}, {'batch_size': 5, 'throughput': 1.523111106400808, 'latency_mean': 3.2646653068065645, 'latency_p50': 3.278621792793274, 'latency_p90': 3.6211261987686156}, {'batch_size': 6, 'throughput': 1.615935336388252, 'latency_mean': 3.6931884968280793, 'latency_p50': 3.683813452720642, 'latency_p90': 4.146997475624085}, {'batch_size': 8, 'throughput': 1.7063165510061946, 'latency_mean': 4.658745280504227, 'latency_p50': 4.681840777397156, 'latency_p90': 5.204143214225769}, {'batch_size': 10, 'throughput': 1.7592871375149404, 'latency_mean': 5.639246915578842, 'latency_p50': 5.686687111854553, 'latency_p90': 6.320453214645386}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-anthropic-ad_3823_v5
is_internal_developer: True
language_model: ChaiML/nemo_anthropic_addict_lexical_1120_run2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2024-11-30
win_ratio: 0.5208977714331033
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': 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': '### 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-v5-mkmlizer
Waiting for job on chaiml-nemo-anthropic-ad-3823-v5-mkmlizer to finish
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ /___/ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ belonging to: ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ║ ║
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: Downloaded to shared memory in 45.899s
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp10s5c9u_, device:0
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: quantized model in 38.264s
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: Processed model ChaiML/nemo_anthropic_addict_lexical_1120_run2 in 84.164s
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v5
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v5/config.json
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v5/special_tokens_map.json
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v5/tokenizer_config.json
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v5/tokenizer.json
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-anthropic-ad-3823-v5/flywheel_model.0.safetensors
chaiml-nemo-anthropic-ad-3823-v5-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.93it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 40.03it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 38.55it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:09, 37.57it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 36.79it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:09, 36.08it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 33.51it/s] Loading 0: 11%|█ | 39/363 [00:01<00:09, 35.66it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:09, 33.98it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 36.37it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:09, 34.35it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:09, 33.75it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:13, 22.85it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 22.01it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.02it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 30.29it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 33.45it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 32.58it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 35.21it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 33.90it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 35.99it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:07, 33.91it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 33.78it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 37.79it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:07, 34.86it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 33.68it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 36.13it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 34.50it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 36.65it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 35.25it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:09, 23.47it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 23.64it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.57it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 33.76it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 35.04it/s] Loading 0: 46%|████▌ | 166/363 [00:05<00:04, 39.85it/s] Loading 0: 47%|████▋ | 171/363 [00:05<00:04, 42.22it/s] Loading 0: 48%|████▊ | 176/363 [00:05<00:04, 38.04it/s] Loading 0: 51%|█████ | 184/363 [00:05<00:03, 46.62it/s] Loading 0: 52%|█████▏ | 190/363 [00:05<00:03, 46.32it/s] Loading 0: 54%|█████▎ | 195/363 [00:05<00:03, 45.61it/s] Loading 0: 56%|█████▌ | 202/363 [00:05<00:03, 49.82it/s] Loading 0: 57%|█████▋ | 208/363 [00:05<00:03, 46.51it/s] Loading 0: 59%|█████▊ | 213/363 [00:06<00:03, 45.10it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:03, 46.14it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:04, 33.61it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 33.34it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 30.84it/s] Loading 0: 65%|██████▍ | 235/363 [00:06<00:03, 32.79it/s] Loading 0: 66%|██████▌ | 239/363 [00:06<00:04, 30.63it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 37.48it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.14it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 37.22it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.49it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 37.78it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 35.90it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 37.54it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 35.52it/s] Loading 0: 78%|███████▊ | 282/363 [00:08<00:02, 37.58it/s] Loading 0: 79%|███████▉ | 286/363 [00:08<00:02, 35.82it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 37.46it/s] Loading 0: 81%|████████▏ | 295/363 [00:08<00:01, 35.33it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 35.06it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:28, 2.10it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.64it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:13, 3.88it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.29it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:05, 7.88it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.56it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:02, 12.83it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:01, 16.54it/s] Loading 0: 94%|█████████▍| 341/363 [00:16<00:01, 18.89it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 22.87it/s] Loading 0: 96%|█████████▋| 350/363 [00:16<00:00, 24.37it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 28.20it/s] Loading 0: 99%|█████████▉| 359/363 [00:16<00:00, 28.54it/s] Loading 0: 100%|██████████| 363/363 [00:16<00:00, 30.96it/s]
Job chaiml-nemo-anthropic-ad-3823-v5-mkmlizer completed after 126.05s with status: succeeded
Stopping job with name chaiml-nemo-anthropic-ad-3823-v5-mkmlizer
Pipeline stage MKMLizer completed in 126.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-anthropic-ad-3823-v5
Waiting for inference service chaiml-nemo-anthropic-ad-3823-v5 to be ready
Inference service chaiml-nemo-anthropic-ad-3823-v5 ready after 140.72984886169434s
Pipeline stage MKMLDeployer completed in 141.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0160839557647705s
Received healthy response to inference request in 1.511141300201416s
Received healthy response to inference request in 1.9091594219207764s
Received healthy response to inference request in 1.4037814140319824s
Received healthy response to inference request in 1.4342727661132812s
5 requests
0 failed requests
5th percentile: 1.4098796844482422
10th percentile: 1.415977954864502
20th percentile: 1.4281744956970215
30th percentile: 1.4496464729309082
40th percentile: 1.480393886566162
50th percentile: 1.511141300201416
60th percentile: 1.67034854888916
70th percentile: 1.8295557975769041
80th percentile: 1.9305443286895752
90th percentile: 1.973314142227173
95th percentile: 1.9946990489959717
99th percentile: 2.0118069744110105
mean time: 1.6548877716064454
Pipeline stage StressChecker completed in 9.71s
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 2.47s
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 2.63s
Shutdown handler de-registered
chaiml-nemo-anthropic-ad_3823_v5 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nemo-anthropic-ad-3823-v5-profiler
Waiting for inference service chaiml-nemo-anthropic-ad-3823-v5-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 2982.78s
Shutdown handler de-registered
chaiml-nemo-anthropic-ad_3823_v5 status is now inactive due to auto deactivation removed underperforming models