chaiml-nemo-espresso-ant_4534

developer_uid: azuruce

submission_id: chaiml-nemo-espresso-ant_4534_v1

model_name: chaiml-nemo-espresso-ant_4534_v1

model_group: ChaiML/nemo_espresso_ant

status: inactive

timestamp: 2024-12-09T22:03:58+00:00

num_battles: 11197

num_wins: 5724

celo_rating: 1271.86

family_friendly_score: 0.5818

family_friendly_standard_error: 0.006975797588806602

submission_type: basic

model_repo: ChaiML/nemo_espresso_ant_llama_241209_albert_v1_sft-3e128a

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6451540907076434, 'latency_mean': 1.549920459985733, 'latency_p50': 1.5458914041519165, 'latency_p90': 1.7122215509414673}, {'batch_size': 4, 'throughput': 1.4859222718177096, 'latency_mean': 2.6807236075401306, 'latency_p50': 2.6821895837783813, 'latency_p90': 2.931996750831604}, {'batch_size': 5, 'throughput': 1.6130733712874603, 'latency_mean': 3.0878432381153105, 'latency_p50': 3.0702948570251465, 'latency_p90': 3.4490994691848753}, {'batch_size': 8, 'throughput': 1.9039450968542115, 'latency_mean': 4.173089183568955, 'latency_p50': 4.16910994052887, 'latency_p90': 4.7018723487854}, {'batch_size': 10, 'throughput': 1.9757759398264287, 'latency_mean': 5.015193700790405, 'latency_p50': 4.978401780128479, 'latency_p90': 5.6574994087219235}, {'batch_size': 12, 'throughput': 2.0452101406310907, 'latency_mean': 5.8122790801525115, 'latency_p50': 5.829890847206116, 'latency_p90': 6.591145157814026}, {'batch_size': 15, 'throughput': 2.0946230830035244, 'latency_mean': 7.089257222414017, 'latency_p50': 7.063526749610901, 'latency_p90': 8.14094455242157}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-nemo-espresso-ant_4534_v1

is_internal_developer: True

language_model: ChaiML/nemo_espresso_ant_llama_241209_albert_v1_sft-3e128a

model_size: 13B

ranking_group: single

throughput_3p7s: 1.81

us_pacific_date: 2024-12-09

win_ratio: 0.5112083593819773

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, '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-nemo-espresso-ant-4534-v1-mkmlizer
Waiting for job on chaiml-nemo-espresso-ant-4534-v1-mkmlizer to finish
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-espresso-ant-4534-v1-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-4534-v1-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-4534-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  https://mk1.ai                                                     ║
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║                                                                     ║
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: Downloaded to shared memory in 49.308s
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqje2k6pp, device:0
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: quantized model in 36.612s
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_241209_albert_v1_sft-3e128a in 85.920s
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-4534-v1
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-4534-v1/config.json
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-4534-v1/special_tokens_map.json
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-4534-v1/tokenizer_config.json
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-4534-v1/tokenizer.json
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-4534-v1/flywheel_model.0.safetensors
chaiml-nemo-espresso-ant-4534-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.67it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.93it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.11it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.11it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.48it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.91it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 48.80it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.80it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.01it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.38it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.55it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.70it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.91it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.23it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.15it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.78it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.86it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 42.10it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 42.09it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 42.07it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 49.53it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:04, 47.36it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 46.45it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.53it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.69it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.58it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 41.16it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.51it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 39.83it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 44.46it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 42.99it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 42.85it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 42.53it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 41.46it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 45.88it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 45.84it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 46.24it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.10it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 31.93it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.94it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.61it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 37.86it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:03, 39.98it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.04it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 39.11it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 37.55it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 38.74it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 38.49it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 37.07it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 41.83it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 42.37it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 42.75it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 42.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:22,  2.63it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.35it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.31it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.06it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.46it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.51it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:01, 19.92it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 21.34it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 28.84it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 31.80it/s]
                                                            
Job chaiml-nemo-espresso-ant-4534-v1-mkmlizer completed after 115.78s with status: succeeded
Stopping job with name chaiml-nemo-espresso-ant-4534-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-espresso-ant-4534-v1
Waiting for inference service chaiml-nemo-espresso-ant-4534-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-espresso-ant-4534-v1 ready after 181.08334112167358s
Pipeline stage MKMLDeployer completed in 181.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.84912109375s
Received healthy response to inference request in 1.4483444690704346s
Received healthy response to inference request in 1.4408249855041504s
Received healthy response to inference request in 1.495077133178711s
Received healthy response to inference request in 1.833770751953125s
5 requests
0 failed requests
5th percentile: 1.4423288822174072
10th percentile: 1.443832778930664
20th percentile: 1.4468405723571778
30th percentile: 1.4576910018920899
40th percentile: 1.4763840675354003
50th percentile: 1.495077133178711
60th percentile: 1.6305545806884765
70th percentile: 1.766032028198242
80th percentile: 1.8368408203125
90th percentile: 1.84298095703125
95th percentile: 1.846051025390625
99th percentile: 1.848507080078125
mean time: 1.6134276866912842
Pipeline stage StressChecker completed in 9.94s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.20s
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 2.03s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_4534_v1 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-espresso-ant-4534-v1-profiler
Waiting for inference service chaiml-nemo-espresso-ant-4534-v1-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 2406.02s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_4534_v1 status is now inactive due to auto deactivation removed underperforming models