chaiml-espresso-ant-llam_6735

developer_uid: azuruce

submission_id: chaiml-espresso-ant-llam_6735_v1

model_name: chaiml-espresso-ant-llam_6735_v1

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-06T01:41:28+00:00

num_battles: 9369

num_wins: 4778

celo_rating: 1270.76

family_friendly_score: 0.5862

family_friendly_standard_error: 0.006965192890365636

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_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': 0.38417179283745195, 'latency_mean': 2.6029362833499907, 'latency_p50': 2.5748307704925537, 'latency_p90': 2.85697865486145}, {'batch_size': 3, 'throughput': 0.8138266641490576, 'latency_mean': 3.674942557811737, 'latency_p50': 3.678658127784729, 'latency_p90': 4.046041941642761}, {'batch_size': 5, 'throughput': 1.0897119462636253, 'latency_mean': 4.573516465425492, 'latency_p50': 4.59760594367981, 'latency_p90': 5.106913232803345}, {'batch_size': 6, 'throughput': 1.171975132462256, 'latency_mean': 5.089695680141449, 'latency_p50': 5.0627201795578, 'latency_p90': 5.624516510963439}, {'batch_size': 10, 'throughput': 1.38009632752565, 'latency_mean': 7.197540451288223, 'latency_p50': 7.237071752548218, 'latency_p90': 8.117036414146423}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-llam_6735_v1

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2024-12-05

win_ratio: 0.5099797203543601

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-6735-v1-mkmlizer
Waiting for job on chaiml-espresso-ant-llam-6735-v1-mkmlizer to finish
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-llam-6735-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-llam-6735-v1-mkmlizer: Downloaded to shared memory in 74.798s
chaiml-espresso-ant-llam-6735-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpun15fptg, device:0
chaiml-espresso-ant-llam-6735-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-llam-6735-v1-mkmlizer: quantized model in 45.287s
chaiml-espresso-ant-llam-6735-v1-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_3epoch_128alpha in 120.085s
chaiml-espresso-ant-llam-6735-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-llam-6735-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-llam-6735-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1
chaiml-espresso-ant-llam-6735-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1/config.json
chaiml-espresso-ant-llam-6735-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1/special_tokens_map.json
chaiml-espresso-ant-llam-6735-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1/tokenizer_config.json
chaiml-espresso-ant-llam-6735-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1/tokenizer.json
chaiml-espresso-ant-llam-6735-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1/flywheel_model.1.safetensors
chaiml-espresso-ant-llam-6735-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-llam-6735-v1/flywheel_model.0.safetensors
chaiml-espresso-ant-llam-6735-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.13it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.04it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.83it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 37.72it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 37.50it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 38.22it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:13, 34.49it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:12, 36.32it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:12, 36.80it/s]
Loading 0:   9%|▉         | 48/507 [00:01<00:15, 30.13it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:18, 24.90it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 23.37it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.39it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.51it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:13, 32.53it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 38.84it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 36.53it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:12, 34.94it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:12, 34.02it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 35.81it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 34.32it/s]
Loading 0:  21%|██        | 104/507 [00:03<00:11, 35.57it/s]
Loading 0:  21%|██▏       | 108/507 [00:03<00:12, 31.91it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.34it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.14it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.45it/s]
Loading 0:  25%|██▌       | 128/507 [00:03<00:11, 33.05it/s]
Loading 0:  26%|██▌       | 132/507 [00:04<00:12, 29.95it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.89it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 29.58it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:10, 34.02it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:11, 31.14it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.00it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:09, 37.78it/s]
Loading 0:  33%|███▎      | 165/507 [00:05<00:09, 37.48it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:13, 25.79it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:12, 26.85it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:12, 26.29it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:11, 28.88it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:11, 27.31it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:09, 35.00it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:09, 34.31it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 36.75it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 34.88it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 37.04it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 35.38it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 35.29it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 35.41it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:10, 25.77it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 25.15it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 32.02it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 30.95it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 32.85it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:08, 31.97it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 34.41it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 32.91it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 34.73it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:07, 32.92it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 34.86it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:07, 32.78it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:06, 36.30it/s]
Loading 0:  56%|█████▋    | 286/507 [00:09<00:09, 24.26it/s]
Loading 0:  57%|█████▋    | 289/507 [00:09<00:08, 24.24it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 24.15it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:07, 29.47it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:07, 29.47it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:18,  1.25s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:30,  1.03s/it]
Loading 0:  61%|██████    | 307/507 [00:24<02:04,  1.60it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:33,  2.12it/s]
Loading 0:  62%|██████▏   | 313/507 [00:24<01:09,  2.81it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:42,  4.42it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:30,  6.00it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:20,  8.64it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 10.91it/s]
Loading 0:  66%|██████▌   | 335/507 [00:25<00:12, 13.66it/s]
Loading 0:  67%|██████▋   | 340/507 [00:25<00:10, 15.20it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:10, 16.32it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:08, 17.93it/s]
Loading 0:  69%|██████▉   | 352/507 [00:25<00:06, 23.05it/s]
Loading 0:  70%|███████   | 356/507 [00:26<00:06, 23.41it/s]
Loading 0:  72%|███████▏  | 363/507 [00:26<00:04, 31.41it/s]
Loading 0:  72%|███████▏  | 367/507 [00:26<00:04, 31.37it/s]
Loading 0:  73%|███████▎  | 372/507 [00:26<00:03, 35.11it/s]
Loading 0:  74%|███████▍  | 377/507 [00:26<00:03, 36.70it/s]
Loading 0:  75%|███████▌  | 382/507 [00:26<00:03, 38.39it/s]
Loading 0:  76%|███████▋  | 387/507 [00:26<00:02, 40.26it/s]
Loading 0:  77%|███████▋  | 392/507 [00:27<00:03, 33.78it/s]
Loading 0:  78%|███████▊  | 396/507 [00:27<00:04, 25.60it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:03, 27.38it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:02, 33.21it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 32.93it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 35.80it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 34.90it/s]
Loading 0:  84%|████████▍ | 426/507 [00:28<00:02, 37.77it/s]
Loading 0:  85%|████████▍ | 430/507 [00:28<00:02, 36.51it/s]
Loading 0:  86%|████████▌ | 435/507 [00:28<00:01, 39.03it/s]
Loading 0:  87%|████████▋ | 440/507 [00:28<00:01, 37.84it/s]
Loading 0:  88%|████████▊ | 444/507 [00:28<00:01, 36.93it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 35.11it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 35.84it/s]
Loading 0:  90%|█████████ | 458/507 [00:31<00:08,  5.81it/s]
Loading 0:  91%|█████████ | 461/507 [00:31<00:06,  6.96it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04,  8.79it/s]
Loading 0:  93%|█████████▎| 470/507 [00:31<00:03, 12.15it/s]
Loading 0:  93%|█████████▎| 474/507 [00:31<00:02, 13.94it/s]
Loading 0:  94%|█████████▍| 479/507 [00:31<00:01, 17.90it/s]
Loading 0:  95%|█████████▌| 483/507 [00:32<00:01, 19.45it/s]
Loading 0:  97%|█████████▋| 490/507 [00:32<00:00, 26.14it/s]
Loading 0:  97%|█████████▋| 494/507 [00:32<00:00, 26.55it/s]
Loading 0:  98%|█████████▊| 498/507 [00:32<00:00, 28.68it/s]
Loading 0:  99%|█████████▉| 502/507 [00:32<00:00, 26.20it/s]
Loading 0: 100%|█████████▉| 506/507 [00:32<00:00, 28.33it/s]
                                                            
Job chaiml-espresso-ant-llam-6735-v1-mkmlizer completed after 147.65s with status: succeeded
Stopping job with name chaiml-espresso-ant-llam-6735-v1-mkmlizer
Pipeline stage MKMLizer completed in 149.81s
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-6735-v1
Waiting for inference service chaiml-espresso-ant-llam-6735-v1 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-6735-v1 ready after 177.71117043495178s
Pipeline stage MKMLDeployer completed in 180.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.993626117706299s
Received healthy response to inference request in 2.664569139480591s
Received healthy response to inference request in 2.3582310676574707s
Received healthy response to inference request in 2.7169346809387207s
Received healthy response to inference request in 2.2605249881744385s
5 requests
0 failed requests
5th percentile: 2.280066204071045
10th percentile: 2.2996074199676513
20th percentile: 2.338689851760864
30th percentile: 2.4194986820220947
40th percentile: 2.5420339107513428
50th percentile: 2.664569139480591
60th percentile: 2.685515356063843
70th percentile: 2.7064615726470946
80th percentile: 2.7722729682922362
90th percentile: 2.8829495429992678
95th percentile: 2.9382878303527833
99th percentile: 2.982558460235596
mean time: 2.598777198791504
Pipeline stage StressChecker completed in 14.28s
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 2.18s
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 2.02s
Shutdown handler de-registered
chaiml-espresso-ant-llam_6735_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 3071.14s
Shutdown handler de-registered
chaiml-espresso-ant-llam_6735_v1 status is now inactive due to auto deactivation removed underperforming models