chaiml-espresso-ant-llam_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_1666_v6

model_name: chaiml-espresso-ant-llam_1666_v6

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T07:44:51+00:00

num_battles: 10433

num_wins: 5192

celo_rating: 1262.79

family_friendly_score: 0.5851999999999999

family_friendly_standard_error: 0.006967653263474008

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.388430256475138, 'latency_mean': 2.5743796825408936, 'latency_p50': 2.557874083518982, 'latency_p90': 2.853071761131287}, {'batch_size': 3, 'throughput': 0.8221687501916466, 'latency_mean': 3.6400874710083007, 'latency_p50': 3.6261556148529053, 'latency_p90': 4.061998891830444}, {'batch_size': 5, 'throughput': 1.1026406371271984, 'latency_mean': 4.516875330209732, 'latency_p50': 4.529754042625427, 'latency_p90': 5.094818353652954}, {'batch_size': 6, 'throughput': 1.1885936211693073, 'latency_mean': 5.014148777723312, 'latency_p50': 4.992601633071899, 'latency_p90': 5.617538595199585}, {'batch_size': 8, 'throughput': 1.3144893166003575, 'latency_mean': 6.047495316267014, 'latency_p50': 6.037739038467407, 'latency_p90': 6.765290021896362}, {'batch_size': 10, 'throughput': 1.3988810299844843, 'latency_mean': 7.077727719545364, 'latency_p50': 7.083288311958313, 'latency_p90': 7.9167397737503045}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_1666_v6

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-12-04

win_ratio: 0.4976516821623694

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-espresso-ant-llam-1666-v6-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v6-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-espresso-ant-llam_1666_v3: ('http://chaiml-espresso-ant-llam-1666-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39102->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-espresso-ant-llam-1666-v6-mkmlizer: Downloaded to shared memory in 45.951s
chaiml-espresso-ant-llam-1666-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcyk80xjl, device:0
chaiml-espresso-ant-llam-1666-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v6-mkmlizer: quantized model in 46.662s
chaiml-espresso-ant-llam-1666-v6-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 92.613s
chaiml-espresso-ant-llam-1666-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6
chaiml-espresso-ant-llam-1666-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6/config.json
chaiml-espresso-ant-llam-1666-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6/tokenizer.json
chaiml-espresso-ant-llam-1666-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v6/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-1666-v6-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.29it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.83it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 35.57it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 35.79it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:14, 32.95it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:13, 35.39it/s]
Loading 0:   7%|▋         | 34/507 [00:01<00:14, 32.47it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:13, 34.89it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:14, 33.08it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 33.01it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:14, 31.31it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:20, 21.57it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:19, 22.65it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:16, 26.13it/s]
Loading 0:  13%|█▎        | 66/507 [00:02<00:17, 24.51it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 27.73it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 31.63it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 30.93it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 35.07it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:13, 30.51it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:12, 33.53it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:13, 29.54it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:11, 35.95it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 33.42it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:16, 24.45it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:17, 22.22it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:15, 25.12it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:12, 29.55it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 27.54it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.91it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 29.10it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:10, 33.56it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:11, 30.64it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 34.66it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 31.27it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 35.90it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 36.76it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 24.97it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:13, 24.03it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 28.75it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:11, 27.33it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:09, 32.04it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 29.27it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 33.29it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:10, 29.92it/s]
Loading 0:  41%|████      | 208/507 [00:06<00:08, 34.34it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:09, 30.28it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:08, 34.63it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 31.05it/s]
Loading 0:  44%|████▍     | 225/507 [00:07<00:12, 22.31it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 24.24it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:09, 28.70it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:10, 26.54it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:08, 30.98it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 28.13it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:07, 32.37it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 28.60it/s]
Loading 0:  52%|█████▏    | 262/507 [00:08<00:07, 32.46it/s]
Loading 0:  52%|█████▏    | 266/507 [00:08<00:08, 29.23it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:07, 33.25it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 29.52it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 33.63it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:09, 24.66it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:09, 24.17it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 24.76it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:07, 29.17it/s]
Loading 0:  59%|█████▉    | 299/507 [00:24<00:07, 29.17it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:04,  1.18s/it]
Loading 0:  60%|█████▉    | 302/507 [00:25<03:20,  1.02it/s]
Loading 0:  61%|██████    | 307/507 [00:25<02:01,  1.65it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:31,  2.15it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:08,  2.84it/s]
Loading 0:  63%|██████▎   | 318/507 [00:25<00:42,  4.42it/s]
Loading 0:  63%|██████▎   | 321/507 [00:25<00:33,  5.53it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:20,  8.75it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 10.88it/s]
Loading 0:  66%|██████▌   | 335/507 [00:26<00:12, 13.38it/s]
Loading 0:  67%|██████▋   | 340/507 [00:26<00:11, 14.76it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:10, 15.96it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:09, 17.53it/s]
Loading 0:  69%|██████▉   | 352/507 [00:26<00:06, 22.48it/s]
Loading 0:  70%|███████   | 356/507 [00:26<00:06, 22.53it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:05, 27.52it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 26.61it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 30.90it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:04, 28.96it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 35.67it/s]
Loading 0:  76%|███████▌  | 385/507 [00:27<00:03, 33.90it/s]
Loading 0:  77%|███████▋  | 389/507 [00:27<00:03, 33.34it/s]
Loading 0:  78%|███████▊  | 393/507 [00:28<00:03, 32.72it/s]
Loading 0:  78%|███████▊  | 397/507 [00:28<00:04, 24.16it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:04, 24.16it/s]
Loading 0:  80%|████████  | 406/507 [00:28<00:03, 28.94it/s]
Loading 0:  81%|████████  | 410/507 [00:28<00:03, 27.06it/s]
Loading 0:  82%|████████▏ | 415/507 [00:28<00:02, 31.65it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:03, 28.85it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 33.28it/s]
Loading 0:  84%|████████▍ | 428/507 [00:29<00:02, 29.94it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:01, 36.81it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 34.62it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 35.78it/s]
Loading 0:  88%|████████▊ | 448/507 [00:29<00:01, 34.33it/s]
Loading 0:  90%|████████▉ | 454/507 [00:29<00:01, 36.40it/s]
Loading 0:  90%|█████████ | 458/507 [00:32<00:08,  6.09it/s]
Loading 0:  91%|█████████ | 461/507 [00:32<00:06,  7.24it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  9.04it/s]
Loading 0:  93%|█████████▎| 470/507 [00:32<00:02, 12.42it/s]
Loading 0:  93%|█████████▎| 474/507 [00:32<00:02, 14.24it/s]
Loading 0:  94%|█████████▍| 479/507 [00:32<00:01, 18.49it/s]
Loading 0:  95%|█████████▌| 483/507 [00:33<00:01, 19.49it/s]
Loading 0:  96%|█████████▋| 488/507 [00:33<00:00, 24.18it/s]
Loading 0:  97%|█████████▋| 492/507 [00:33<00:00, 23.78it/s]
Loading 0:  98%|█████████▊| 497/507 [00:33<00:00, 28.64it/s]
Loading 0:  99%|█████████▉| 501/507 [00:33<00:00, 27.24it/s]
Loading 0: 100%|█████████▉| 506/507 [00:33<00:00, 31.88it/s]
                                                            
Job chaiml-espresso-ant-llam-1666-v6-mkmlizer completed after 132.19s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v6-mkmlizer
Pipeline stage MKMLizer completed in 133.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-espresso-ant-llam-1666-v6
Waiting for inference service chaiml-espresso-ant-llam-1666-v6 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
Inference service chaiml-espresso-ant-llam-1666-v6 ready after 184.65870475769043s
Pipeline stage MKMLDeployer completed in 186.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.098184108734131s
Received healthy response to inference request in 2.2911343574523926s
Received healthy response to inference request in 2.328782796859741s
Received healthy response to inference request in 2.266200065612793s
Received healthy response to inference request in 2.276859760284424s
5 requests
0 failed requests
5th percentile: 2.268332004547119
10th percentile: 2.2704639434814453
20th percentile: 2.2747278213500977
30th percentile: 2.2797146797180177
40th percentile: 2.285424518585205
50th percentile: 2.2911343574523926
60th percentile: 2.306193733215332
70th percentile: 2.3212531089782713
80th percentile: 2.4826630592346195
90th percentile: 2.790423583984375
95th percentile: 2.9443038463592526
99th percentile: 3.067408056259155
mean time: 2.4522322177886964
Pipeline stage StressChecker completed in 13.83s
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 2.51s
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 2.31s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_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 3140.30s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v6 status is now inactive due to auto deactivation removed underperforming models