chaiml-1-5-k-payload-lex_9640

developer_uid: azuruce

submission_id: chaiml-1-5-k-payload-lex_9640_v1

model_name: 3epoch

model_group: ChaiML/1_5_k_payload_lex

status: inactive

timestamp: 2024-11-22T18:59:56+00:00

num_battles: 15634

num_wins: 8301

celo_rating: 1273.17

family_friendly_score: 0.5811999999999999

family_friendly_standard_error: 0.006977199438170017

submission_type: basic

model_repo: ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0-3epoch

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38801069574149727, 'latency_mean': 2.5771502304077147, 'latency_p50': 2.604913592338562, 'latency_p90': 2.8520184278488157}, {'batch_size': 3, 'throughput': 0.8221785602255973, 'latency_mean': 3.633009657859802, 'latency_p50': 3.621600031852722, 'latency_p90': 3.9546159744262694}, {'batch_size': 5, 'throughput': 1.080359204939169, 'latency_mean': 4.597867429256439, 'latency_p50': 4.618366122245789, 'latency_p90': 5.10373785495758}, {'batch_size': 6, 'throughput': 1.1721783342250867, 'latency_mean': 5.088757051229477, 'latency_p50': 5.076189160346985, 'latency_p90': 5.757612109184265}, {'batch_size': 10, 'throughput': 1.3846093627807858, 'latency_mean': 7.152297505140305, 'latency_p50': 7.158968687057495, 'latency_p90': 8.125670671463013}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: 3epoch

is_internal_developer: True

language_model: ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0-3epoch

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-11-22

win_ratio: 0.5309581680951772

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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-1-5-k-payload-lex-9640-v1-mkmlizer
Waiting for job on chaiml-1-5-k-payload-lex-9640-v1-mkmlizer to finish
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║       /___/                                                         ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ║                                                                     ║
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: Downloaded to shared memory in 88.102s
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5rdjr2z4, device:0
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: quantized model in 43.007s
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: Processed model ChaiML/1_5_k_payload_lexical_filtered_for_albert-run2-rank0-3epoch in 131.109s
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1/config.json
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1/special_tokens_map.json
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1/tokenizer_config.json
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1/tokenizer.json
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1/flywheel_model.1.safetensors
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1-5-k-payload-lex-9640-v1/flywheel_model.0.safetensors
chaiml-1-5-k-payload-lex-9640-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:22, 22.34it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:13, 37.34it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.58it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:13, 37.20it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 37.16it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 38.16it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:12, 38.28it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:12, 38.91it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 38.98it/s]
Loading 0:   9%|▉         | 48/507 [00:01<00:15, 30.52it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:18, 24.01it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 22.85it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.91it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:13, 32.08it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 35.36it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 37.08it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:09, 42.54it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 41.13it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.13it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:10, 40.35it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:11, 34.80it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 30.00it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 28.78it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 29.15it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.75it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.87it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:09, 37.65it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 36.23it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.57it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 36.48it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.72it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 37.41it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 37.64it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:11, 29.01it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 30.01it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 29.72it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.83it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 35.21it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 38.36it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 36.47it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:08, 37.66it/s]
Loading 0:  41%|████      | 207/507 [00:05<00:07, 39.76it/s]
Loading 0:  42%|████▏     | 212/507 [00:06<00:08, 33.59it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 39.52it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 36.34it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:09, 30.52it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 29.27it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.03it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 33.90it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.84it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.26it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.46it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.14it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 37.57it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 35.12it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:06, 36.40it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 34.72it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 37.45it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 25.15it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.27it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.27it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:44,  1.26it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:22,  1.44it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.07it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:16,  2.56it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<00:59,  3.26it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:38,  4.90it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.50it/s]
Loading 0:  64%|██████▍   | 327/507 [00:23<00:19,  9.20it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.54it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:11, 14.45it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 16.31it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.94it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:07, 19.95it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 25.95it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 27.84it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 32.25it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 32.66it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 36.38it/s]
Loading 0:  74%|███████▍  | 377/507 [00:25<00:03, 37.82it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 38.99it/s]
Loading 0:  76%|███████▋  | 387/507 [00:25<00:02, 40.52it/s]
Loading 0:  77%|███████▋  | 392/507 [00:25<00:03, 35.59it/s]
Loading 0:  78%|███████▊  | 396/507 [00:26<00:04, 27.53it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 28.81it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 35.21it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.90it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.24it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 34.93it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 37.50it/s]
Loading 0:  85%|████████▍ | 430/507 [00:26<00:02, 35.02it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 36.73it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.83it/s]
Loading 0:  88%|████████▊ | 445/507 [00:27<00:01, 40.06it/s]
Loading 0:  89%|████████▉ | 450/507 [00:27<00:01, 42.33it/s]
Loading 0:  90%|████████▉ | 455/507 [00:29<00:08,  6.40it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:06,  7.94it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:03, 11.02it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 15.79it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 18.09it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 22.19it/s]
Loading 0:  96%|█████████▌| 486/507 [00:30<00:00, 25.56it/s]
Loading 0:  97%|█████████▋| 491/507 [00:30<00:00, 28.31it/s]
Loading 0:  98%|█████████▊| 496/507 [00:30<00:00, 32.09it/s]
Loading 0:  99%|█████████▉| 501/507 [00:30<00:00, 30.37it/s]
                                                            
Job chaiml-1-5-k-payload-lex-9640-v1-mkmlizer completed after 157.28s with status: succeeded
Stopping job with name chaiml-1-5-k-payload-lex-9640-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1-5-k-payload-lex-9640-v1
Waiting for inference service chaiml-1-5-k-payload-lex-9640-v1 to be ready
Inference service chaiml-1-5-k-payload-lex-9640-v1 ready after 231.04368019104004s
Pipeline stage MKMLDeployer completed in 231.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8608412742614746s
Received healthy response to inference request in 2.4893388748168945s
Received healthy response to inference request in 2.426551103591919s
Received healthy response to inference request in 2.656205415725708s
Received healthy response to inference request in 2.265970230102539s
5 requests
0 failed requests
5th percentile: 2.298086404800415
10th percentile: 2.330202579498291
20th percentile: 2.394434928894043
30th percentile: 2.439108657836914
40th percentile: 2.464223766326904
50th percentile: 2.4893388748168945
60th percentile: 2.55608549118042
70th percentile: 2.622832107543945
80th percentile: 2.6971325874328613
90th percentile: 2.778986930847168
95th percentile: 2.8199141025543213
99th percentile: 2.852655839920044
mean time: 2.539781379699707
Pipeline stage StressChecker completed in 14.29s
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 2.66s
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 2.76s
Shutdown handler de-registered
chaiml-1-5-k-payload-lex_9640_v1 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 3339.77s
Shutdown handler de-registered
chaiml-1-5-k-payload-lex_9640_v1 status is now inactive due to auto deactivation removed underperforming models