chaiml-espresso-ant-llam_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_1666_v2

model_name: chaiml-espresso-ant-llam_1666_v2

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T05:53:36+00:00

num_battles: 9054

num_wins: 4453

celo_rating: 1256.62

family_friendly_score: 0.5873999999999999

family_friendly_standard_error: 0.006962201376001702

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': 0.3888022756214061, 'latency_mean': 2.5719448816776276, 'latency_p50': 2.577751040458679, 'latency_p90': 2.8322896003723144}, {'batch_size': 3, 'throughput': 0.834666673416748, 'latency_mean': 3.5941846573352816, 'latency_p50': 3.6073354482650757, 'latency_p90': 3.9156989812850953}, {'batch_size': 5, 'throughput': 1.100150913948851, 'latency_mean': 4.533701308965683, 'latency_p50': 4.50981867313385, 'latency_p90': 5.064200687408447}, {'batch_size': 6, 'throughput': 1.1752218510023507, 'latency_mean': 5.08186537861824, 'latency_p50': 5.100030779838562, 'latency_p90': 5.596109700202942}, {'batch_size': 10, 'throughput': 1.3981423361875793, 'latency_mean': 7.089037692546844, 'latency_p50': 7.083418846130371, 'latency_p90': 8.044437336921693}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_1666_v2

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.87

us_pacific_date: 2024-12-04

win_ratio: 0.4918268168765187

generation_params: {'temperature': 0.9, '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-v2-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-1666-v2-mkmlizer to finish
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-1666-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-1666-v2-mkmlizer: Downloaded to shared memory in 46.448s
chaiml-espresso-ant-llam-1666-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpprcwaixo, device:0
chaiml-espresso-ant-llam-1666-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-1666-v2-mkmlizer: quantized model in 49.336s
chaiml-espresso-ant-llam-1666-v2-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 95.784s
chaiml-espresso-ant-llam-1666-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-1666-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-1666-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2
chaiml-espresso-ant-llam-1666-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2/config.json
chaiml-espresso-ant-llam-1666-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2/special_tokens_map.json
chaiml-espresso-ant-llam-1666-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2/tokenizer_config.json
chaiml-espresso-ant-llam-1666-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2/tokenizer.json
chaiml-espresso-ant-llam-1666-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-1666-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-1666-v2/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-1666-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:24, 20.69it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:17, 28.92it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:19, 24.73it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:16, 28.80it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:18, 25.67it/s]
Loading 0:   6%|▌         | 28/507 [00:01<00:16, 29.32it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:18, 25.86it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:16, 29.23it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:17, 26.20it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:15, 29.83it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:16, 27.21it/s]
Loading 0:  10%|█         | 53/507 [00:02<00:24, 18.58it/s]
Loading 0:  11%|█         | 56/507 [00:02<00:25, 17.93it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:19, 22.97it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.55it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 27.39it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 30.08it/s]
Loading 0:  16%|█▌        | 80/507 [00:03<00:14, 29.20it/s]
Loading 0:  17%|█▋        | 85/507 [00:03<00:12, 32.92it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:14, 28.91it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:13, 31.67it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:15, 27.13it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:13, 30.43it/s]
Loading 0:  21%|██        | 107/507 [00:04<00:15, 26.43it/s]
Loading 0:  22%|██▏       | 112/507 [00:04<00:13, 29.40it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:20, 18.91it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:17, 21.83it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:15, 25.19it/s]
Loading 0:  26%|██▌       | 131/507 [00:05<00:15, 23.56it/s]
Loading 0:  27%|██▋       | 136/507 [00:05<00:13, 27.03it/s]
Loading 0:  28%|██▊       | 140/507 [00:05<00:14, 24.94it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:12, 28.16it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:13, 25.73it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:12, 28.91it/s]
Loading 0:  31%|███       | 158/507 [00:06<00:13, 26.19it/s]
Loading 0:  32%|███▏      | 163/507 [00:06<00:11, 29.88it/s]
Loading 0:  33%|███▎      | 168/507 [00:06<00:11, 30.77it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:16, 19.97it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:16, 20.22it/s]
Loading 0:  36%|███▌      | 181/507 [00:07<00:13, 24.34it/s]
Loading 0:  36%|███▋      | 185/507 [00:07<00:13, 23.89it/s]
Loading 0:  37%|███▋      | 190/507 [00:07<00:11, 28.15it/s]
Loading 0:  38%|███▊      | 194/507 [00:07<00:11, 26.88it/s]
Loading 0:  39%|███▉      | 199/507 [00:07<00:09, 31.53it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:10, 28.66it/s]
Loading 0:  41%|████▏     | 210/507 [00:07<00:08, 35.48it/s]
Loading 0:  42%|████▏     | 214/507 [00:08<00:08, 33.62it/s]
Loading 0:  43%|████▎     | 218/507 [00:08<00:08, 32.42it/s]
Loading 0:  44%|████▍     | 222/507 [00:08<00:09, 30.63it/s]
Loading 0:  45%|████▍     | 226/507 [00:08<00:14, 20.03it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:13, 20.35it/s]
Loading 0:  46%|████▋     | 235/507 [00:09<00:11, 24.06it/s]
Loading 0:  47%|████▋     | 239/507 [00:09<00:11, 23.11it/s]
Loading 0:  48%|████▊     | 244/507 [00:09<00:09, 26.87it/s]
Loading 0:  49%|████▉     | 248/507 [00:09<00:10, 25.16it/s]
Loading 0:  50%|████▉     | 253/507 [00:09<00:08, 28.81it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:09, 25.73it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:08, 28.70it/s]
Loading 0:  52%|█████▏    | 266/507 [00:10<00:09, 25.35it/s]
Loading 0:  53%|█████▎    | 271/507 [00:10<00:08, 28.29it/s]
Loading 0:  54%|█████▍    | 275/507 [00:10<00:09, 25.58it/s]
Loading 0:  55%|█████▌    | 280/507 [00:10<00:07, 28.90it/s]
Loading 0:  56%|█████▌    | 284/507 [00:10<00:10, 20.55it/s]
Loading 0:  57%|█████▋    | 287/507 [00:11<00:11, 18.44it/s]
Loading 0:  58%|█████▊    | 293/507 [00:11<00:10, 21.32it/s]
Loading 0:  59%|█████▉    | 298/507 [00:11<00:08, 24.90it/s]
Loading 0:  59%|█████▉    | 299/507 [00:21<00:08, 24.90it/s]
Loading 0:  59%|█████▉    | 300/507 [00:27<04:21,  1.26s/it]
Loading 0:  60%|█████▉    | 302/507 [00:27<03:36,  1.05s/it]
Loading 0:  61%|██████    | 307/507 [00:27<02:11,  1.52it/s]
Loading 0:  61%|██████    | 310/507 [00:28<01:38,  1.99it/s]
Loading 0:  62%|██████▏   | 313/507 [00:28<01:14,  2.62it/s]
Loading 0:  62%|██████▏   | 316/507 [00:28<00:55,  3.47it/s]
Loading 0:  63%|██████▎   | 320/507 [00:28<00:38,  4.89it/s]
Loading 0:  64%|██████▍   | 325/507 [00:28<00:24,  7.38it/s]
Loading 0:  65%|██████▍   | 329/507 [00:28<00:19,  9.24it/s]
Loading 0:  66%|██████▌   | 334/507 [00:28<00:13, 12.72it/s]
Loading 0:  67%|██████▋   | 339/507 [00:29<00:10, 16.12it/s]
Loading 0:  68%|██████▊   | 343/507 [00:29<00:11, 14.36it/s]
Loading 0:  68%|██████▊   | 347/507 [00:29<00:10, 15.69it/s]
Loading 0:  69%|██████▉   | 352/507 [00:29<00:07, 19.48it/s]
Loading 0:  70%|███████   | 356/507 [00:29<00:07, 20.11it/s]
Loading 0:  71%|███████   | 361/507 [00:30<00:06, 23.85it/s]
Loading 0:  72%|███████▏  | 365/507 [00:30<00:06, 22.65it/s]
Loading 0:  73%|███████▎  | 370/507 [00:30<00:05, 26.30it/s]
Loading 0:  74%|███████▍  | 374/507 [00:30<00:05, 24.54it/s]
Loading 0:  75%|███████▍  | 379/507 [00:30<00:04, 28.33it/s]
Loading 0:  76%|███████▌  | 383/507 [00:30<00:04, 26.06it/s]
Loading 0:  77%|███████▋  | 388/507 [00:31<00:04, 29.58it/s]
Loading 0:  77%|███████▋  | 392/507 [00:31<00:04, 27.19it/s]
Loading 0:  78%|███████▊  | 395/507 [00:31<00:05, 19.47it/s]
Loading 0:  79%|███████▉  | 401/507 [00:31<00:04, 22.17it/s]
Loading 0:  80%|████████  | 406/507 [00:31<00:03, 26.14it/s]
Loading 0:  81%|████████  | 410/507 [00:32<00:03, 24.43it/s]
Loading 0:  82%|████████▏ | 415/507 [00:32<00:03, 28.48it/s]
Loading 0:  83%|████████▎ | 419/507 [00:32<00:03, 26.57it/s]
Loading 0:  84%|████████▎ | 424/507 [00:32<00:02, 30.42it/s]
Loading 0:  84%|████████▍ | 428/507 [00:32<00:02, 27.33it/s]
Loading 0:  85%|████████▌ | 433/507 [00:32<00:02, 31.49it/s]
Loading 0:  86%|████████▌ | 437/507 [00:32<00:02, 28.17it/s]
Loading 0:  87%|████████▋ | 442/507 [00:33<00:01, 32.77it/s]
Loading 0:  88%|████████▊ | 446/507 [00:33<00:02, 30.19it/s]
Loading 0:  90%|████████▉ | 454/507 [00:33<00:01, 36.95it/s]
Loading 0:  90%|█████████ | 458/507 [00:35<00:07,  6.52it/s]
Loading 0:  91%|█████████ | 461/507 [00:35<00:05,  7.67it/s]
Loading 0:  92%|█████████▏| 465/507 [00:35<00:04,  9.48it/s]
Loading 0:  93%|█████████▎| 470/507 [00:35<00:02, 12.94it/s]
Loading 0:  93%|█████████▎| 474/507 [00:36<00:02, 14.89it/s]
Loading 0:  94%|█████████▍| 479/507 [00:36<00:01, 18.86it/s]
Loading 0:  95%|█████████▌| 483/507 [00:36<00:01, 19.96it/s]
Loading 0:  96%|█████████▋| 489/507 [00:36<00:00, 26.48it/s]
Loading 0:  97%|█████████▋| 493/507 [00:36<00:00, 25.97it/s]
Loading 0:  98%|█████████▊| 499/507 [00:36<00:00, 30.37it/s]
Loading 0:  99%|█████████▉| 503/507 [00:36<00:00, 30.08it/s]
                                                            
Job chaiml-espresso-ant-llam-1666-v2-mkmlizer completed after 132.78s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-1666-v2-mkmlizer
Pipeline stage MKMLizer completed in 133.95s
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-espresso-ant-llam-1666-v2
Waiting for inference service chaiml-espresso-ant-llam-1666-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-espresso-ant-llam-1666-v2 ready after 165.048113822937s
Pipeline stage MKMLDeployer completed in 166.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7122936248779297s
Received healthy response to inference request in 2.302424907684326s
Received healthy response to inference request in 2.6762490272521973s
Received healthy response to inference request in 2.305769681930542s
Received healthy response to inference request in 2.471355676651001s
5 requests
0 failed requests
5th percentile: 2.3030938625335695
10th percentile: 2.3037628173828124
20th percentile: 2.3051007270812987
30th percentile: 2.3388868808746337
40th percentile: 2.4051212787628176
50th percentile: 2.471355676651001
60th percentile: 2.5533130168914795
70th percentile: 2.635270357131958
80th percentile: 2.683457946777344
90th percentile: 2.6978757858276365
95th percentile: 2.705084705352783
99th percentile: 2.7108518409729006
mean time: 2.4936185836791993
Pipeline stage StressChecker completed in 13.76s
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 2.13s
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-espresso-ant-llam_1666_v2 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 3184.36s
Shutdown handler de-registered
chaiml-espresso-ant-llam_1666_v2 status is now inactive due to auto deactivation removed underperforming models