developer_uid: azuruce
submission_id: chaiml-nemo-espresso-ant_5543_v6
model_name: chaiml-nemo-espresso-ant_5543_v6
model_group: ChaiML/nemo_espresso_ant
status: inactive
timestamp: 2024-12-06T16:04:05+00:00
num_battles: 8105
num_wins: 4229
celo_rating: 1276.91
family_friendly_score: 0.5774
family_friendly_standard_error: 0.006985831947592212
submission_type: basic
model_repo: ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6166948307720526, 'latency_mean': 1.6214796352386474, 'latency_p50': 1.6143203973770142, 'latency_p90': 1.7960010051727295}, {'batch_size': 3, 'throughput': 1.1653901149414119, 'latency_mean': 2.565471091270447, 'latency_p50': 2.5674631595611572, 'latency_p90': 2.8627868413925173}, {'batch_size': 5, 'throughput': 1.4111476710781596, 'latency_mean': 3.5215321767330168, 'latency_p50': 3.5210657119750977, 'latency_p90': 3.8905799627304076}, {'batch_size': 6, 'throughput': 1.4982866927790108, 'latency_mean': 3.9876114106178284, 'latency_p50': 3.9858736991882324, 'latency_p90': 4.48034815788269}, {'batch_size': 8, 'throughput': 1.5666157128283598, 'latency_mean': 5.071267492771149, 'latency_p50': 5.129601836204529, 'latency_p90': 5.6825624942779545}, {'batch_size': 10, 'throughput': 1.5939140003405918, 'latency_mean': 6.235367513895035, 'latency_p50': 6.3129962682724, 'latency_p90': 6.978469467163086}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-ant_5543_v6
is_internal_developer: True
language_model: ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_size: 13B
ranking_group: single
throughput_3p7s: 1.45
us_pacific_date: 2024-12-06
win_ratio: 0.5217766810610734
generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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-nemo-espresso-ant-5543-v6-mkmlizer
Waiting for job on chaiml-nemo-espresso-ant-5543-v6-mkmlizer to finish
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ /___/ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ belonging to: ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ║ ║
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: Downloaded to shared memory in 28.860s
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpupw5gw8b, device:0
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: quantized model in 35.696s
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 64.556s
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v6
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v6/config.json
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v6/special_tokens_map.json
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v6/tokenizer_config.json
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v6/tokenizer.json
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v6/flywheel_model.0.safetensors
chaiml-nemo-espresso-ant-5543-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 27.53it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 47.24it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 43.20it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 42.21it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.79it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.79it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.46it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.31it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 48.82it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 37.64it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 37.41it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 41.67it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 43.35it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:07, 36.76it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 45.61it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 45.13it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 44.87it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 48.55it/s] Loading 0: 31%|███ | 113/363 [00:02<00:05, 44.00it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 43.81it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 51.80it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 44.87it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.34it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.93it/s] Loading 0: 40%|████ | 146/363 [00:03<00:05, 36.49it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 35.21it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 42.50it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 42.09it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 42.48it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 47.73it/s] Loading 0: 50%|████▉ | 180/363 [00:04<00:03, 48.31it/s] Loading 0: 51%|█████ | 185/363 [00:04<00:04, 39.98it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.99it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.45it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.73it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.00it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 47.52it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 38.81it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 38.12it/s] Loading 0: 64%|██████▍ | 233/363 [00:05<00:03, 40.42it/s] Loading 0: 66%|██████▌ | 239/363 [00:05<00:03, 39.14it/s] Loading 0: 68%|██████▊ | 246/363 [00:05<00:02, 43.99it/s] Loading 0: 69%|██████▉ | 251/363 [00:05<00:02, 44.85it/s] Loading 0: 71%|███████ | 257/363 [00:05<00:02, 41.71it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:01, 49.63it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.62it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 40.69it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 43.14it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 41.40it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 40.47it/s] Loading 0: 82%|████████▏ | 297/363 [00:06<00:01, 42.30it/s] Loading 0: 83%|████████▎ | 303/363 [00:07<00:01, 42.87it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:21, 2.52it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:15, 3.25it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:08, 5.33it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.30it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.42it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.45it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.01it/s] Loading 0: 96%|█████████▋| 350/363 [00:14<00:00, 21.13it/s] Loading 0: 98%|█████████▊| 357/363 [00:14<00:00, 25.28it/s]
Job chaiml-nemo-espresso-ant-5543-v6-mkmlizer completed after 93.67s with status: succeeded
Stopping job with name chaiml-nemo-espresso-ant-5543-v6-mkmlizer
Pipeline stage MKMLizer completed in 95.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-espresso-ant-5543-v6
Waiting for inference service chaiml-nemo-espresso-ant-5543-v6 to be ready
Inference service chaiml-nemo-espresso-ant-5543-v6 ready after 190.48305821418762s
Pipeline stage MKMLDeployer completed in 192.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.400190353393555s
Received healthy response to inference request in 4.964332342147827s
Received healthy response to inference request in 7.559894800186157s
Received healthy response to inference request in 2.0806398391723633s
Received healthy response to inference request in 3.860670804977417s
5 requests
0 failed requests
5th percentile: 2.436646032333374
10th percentile: 2.792652225494385
20th percentile: 3.5046646118164064
30th percentile: 3.9685747146606447
40th percentile: 4.184382534027099
50th percentile: 4.400190353393555
60th percentile: 4.6258471488952635
70th percentile: 4.851503944396972
80th percentile: 5.4834448337554935
90th percentile: 6.521669816970825
95th percentile: 7.040782308578491
99th percentile: 7.456072301864624
mean time: 4.573145627975464
%s, retrying in %s seconds...
Received healthy response to inference request in 1.722167730331421s
Received healthy response to inference request in 1.8047692775726318s
Received healthy response to inference request in 1.8872976303100586s
Received healthy response to inference request in 2.008054494857788s
Received healthy response to inference request in 1.8617897033691406s
5 requests
0 failed requests
5th percentile: 1.7386880397796631
10th percentile: 1.7552083492279054
20th percentile: 1.7882489681243896
30th percentile: 1.8161733627319336
40th percentile: 1.838981533050537
50th percentile: 1.8617897033691406
60th percentile: 1.8719928741455079
70th percentile: 1.882196044921875
80th percentile: 1.9114490032196045
90th percentile: 1.9597517490386962
95th percentile: 1.9839031219482421
99th percentile: 2.0032242202758788
mean time: 1.856815767288208
Pipeline stage StressChecker completed in 34.88s
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 2.23s
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 2.05s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_5543_v6 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2710.66s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_5543_v6 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1