chaiml-nemo-20241017-tie_8098

submission_id: chaiml-nemo-20241017-tie_8098_v9

developer_uid: chai_backend_admin

best_of: 4

celo_rating: 1248.31

display_name: chaiml-nemo-20241017-tie_8098_v9

family_friendly_score: 0.5928

family_friendly_standard_error: 0.006948210704922527

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}

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|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

latencies: [{'batch_size': 1, 'throughput': 0.6247404029819161, 'latency_mean': 1.6005967736244202, 'latency_p50': 1.6062134504318237, 'latency_p90': 1.7575963258743286}, {'batch_size': 3, 'throughput': 1.2482636490783556, 'latency_mean': 2.3964965188503267, 'latency_p50': 2.400490641593933, 'latency_p90': 2.6517409563064573}, {'batch_size': 5, 'throughput': 1.581831025386693, 'latency_mean': 3.14875030875206, 'latency_p50': 3.1224098205566406, 'latency_p90': 3.504009461402893}, {'batch_size': 6, 'throughput': 1.6874111264161966, 'latency_mean': 3.531926876306534, 'latency_p50': 3.542679786682129, 'latency_p90': 4.0099786758422855}, {'batch_size': 8, 'throughput': 1.8531035445304427, 'latency_mean': 4.293656495809555, 'latency_p50': 4.263140082359314, 'latency_p90': 4.796314525604248}, {'batch_size': 10, 'throughput': 1.9229270326060455, 'latency_mean': 5.162538341283798, 'latency_p50': 5.162138104438782, 'latency_p90': 5.830679225921631}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/nemo-20241017-tie

model_name: chaiml-nemo-20241017-tie_8098_v9

model_num_parameters: 12772070400.0

model_repo: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

model_size: 13B

num_battles: 7614

num_wins: 3827

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.74

timestamp: 2024-11-12T01:29:27+00:00

us_pacific_date: 2024-11-11

win_ratio: 0.5026267402153927

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-20241017-tie-8098-v9-mkmlizer
Waiting for job on chaiml-nemo-20241017-tie-8098-v9-mkmlizer to finish
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  Version: 0.11.33                                                   ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: Downloaded to shared memory in 41.330s
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmv_bu5sm, device:0
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission rinen0721-mistral12b-exp5_v3: ('http://rinen0721-mistral12b-exp5-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39392->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: quantized model in 37.326s
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 78.657s
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v9
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v9/config.json
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v9/special_tokens_map.json
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v9/tokenizer_config.json
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v9/tokenizer.json
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v9/flywheel_model.0.safetensors
chaiml-nemo-20241017-tie-8098-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:53,  3.14s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:01,  1.18it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:47,  3.26it/s]
Loading 0:   5%|▌         | 19/363 [00:06<01:01,  5.61it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:43,  7.81it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:25, 12.90it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:19, 16.59it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:19, 16.71it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:14, 21.75it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:12, 24.83it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 28.19it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:09, 32.12it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:09, 30.80it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 39.81it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:07, 38.38it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:06, 39.40it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:05, 44.77it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:05, 43.83it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:05, 43.36it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 47.60it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:05, 45.61it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:07, 32.47it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.97it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 37.13it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 38.88it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 39.79it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:06, 35.08it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 40.49it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 39.57it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 40.74it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 41.23it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 39.21it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 42.48it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 43.92it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 44.76it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 44.89it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 26.26it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 33.35it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 34.92it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 36.92it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 39.21it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:03, 33.46it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 40.40it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:03, 39.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 40.05it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 39.98it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 38.31it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 38.24it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 34.65it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 40.15it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:02, 37.81it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 26.84it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 27.78it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 30.83it/s]
Loading 0:  82%|████████▏ | 296/363 [00:13<00:02, 31.71it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 36.77it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 37.88it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 35.85it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 44.24it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:00, 43.32it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:00, 42.21it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 46.53it/s]
Loading 0:  94%|█████████▍| 342/363 [00:14<00:00, 44.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 44.96it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 45.44it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 38.43it/s]
                                                            
Job chaiml-nemo-20241017-tie-8098-v9-mkmlizer completed after 104.12s with status: succeeded
Stopping job with name chaiml-nemo-20241017-tie-8098-v9-mkmlizer
Pipeline stage MKMLizer completed in 104.71s
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-20241017-tie-8098-v9
Waiting for inference service chaiml-nemo-20241017-tie-8098-v9 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
Failed to get response for submission bbchicago-nana-nemo-12b-v1-0_v8: ('http://bbchicago-nana-nemo-12b-v1-0-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-nemo-20241017-tie-8098-v9 ready after 180.7040719985962s
Pipeline stage MKMLDeployer completed in 181.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8003308773040771s
Received healthy response to inference request in 1.4151694774627686s
Received healthy response to inference request in 1.4488139152526855s
Received healthy response to inference request in 1.3835651874542236s
Received healthy response to inference request in 1.3600678443908691s
5 requests
0 failed requests
5th percentile: 1.36476731300354
10th percentile: 1.369466781616211
20th percentile: 1.3788657188415527
30th percentile: 1.3898860454559325
40th percentile: 1.4025277614593505
50th percentile: 1.4151694774627686
60th percentile: 1.4286272525787354
70th percentile: 1.4420850276947021
80th percentile: 1.519117307662964
90th percentile: 1.6597240924835206
95th percentile: 1.7300274848937987
99th percentile: 1.7862701988220215
mean time: 1.4815894603729247
Pipeline stage StressChecker completed in 8.94s
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 3.37s
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 2.87s
Shutdown handler de-registered
chaiml-nemo-20241017-tie_8098_v9 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 2432.67s
Shutdown handler de-registered
chaiml-nemo-20241017-tie_8098_v9 status is now inactive due to auto deactivation removed underperforming models